© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 61343
    Prev
    Next
    INDEX
    Explanations

    hypothetical, open-ended choice questions that invite someone to imagine a scenario and explain their reasoning (often framed as what they would do, be, or choose and why).

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    open-ended, second-person hypothetical prompts that ask the reader to imagine choices or scenarios and explain their reasoning.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mph
    -0.08
     MediaTek
    -0.07
     CES
    -0.07
    blue
    -0.07
    urious
    -0.07
    Ce
    -0.07
    曲折
    -0.07
    peech
    -0.07
    fact
    -0.07
     grads
    -0.06
    POSITIVE LOGITS
    #SBATCH
    0.07
     commercially
    0.06
    붇
    0.06
     İnsan
    0.06
    护
    0.06
    �
    0.06
    옮
    0.06
    不过是
    0.06
    �
    0.06
    ItemId
    0.06
    Activations Density 0.056%

    No Known Activations