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

    Neuronpedia

    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. 45904
    Prev
    Next
    INDEX
    Explanations

    tagged posts

    np_max-act · gemini-2.0-flash

    blog tag/archive headers indicating a topic, especially the lines introducing and naming the tagged subject.

    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
    2
    -0.09
    3
    -0.09
    6
    -0.08
    5
    -0.08
    -address
    -0.07
    rick
    -0.07
     Launch
    -0.07
    1
    -0.07
     stunning
    -0.07
    在
    -0.07
    POSITIVE LOGITS
     blackout
    0.06
    .filePath
    0.06
    _CARD
    0.06
    ϑ
    0.06
     operative
    0.06
    Orth
    0.06
     underworld
    0.06
    .@
    0.06
    Ini
    0.06
     Swap
    0.06
    Activations Density 51.363%

    No Known Activations