© 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. 11-RESID-POST-AA
    11. 110671
    Prev
    Next
    INDEX
    Explanations

    technical questions and answers

    np_max-act · gemini-2.0-flash

    tokens related to programming/code queries (language names, libraries, code-related terms).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PACK
    -0.07
     volunte
    -0.07
     totalTime
    -0.07
     posY
    -0.07
     Lans
    -0.07
     RouterModule
    -0.07
     Trinity
    -0.07
    pNet
    -0.06
     recommends
    -0.06
    _filepath
    -0.06
    POSITIVE LOGITS
    央行
    0.07
    对她
    0.07
    臂
    0.06
    ット
    0.06
    есс
    0.06
     region
    0.06
     nuova
    0.06
    hat
    0.06
     discounts
    0.06
    对我
    0.06
    Activations Density 0.126%

    No Known Activations