© 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 EvalsExportsinterp-engineNEWAPI 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. 107687
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    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
     racially
    -0.07
    paragus
    -0.07
    可想而
    -0.07
    ثلاث
    -0.07
    /db
    -0.07
    委员
    -0.07
     ABC
    -0.06
     halls
    -0.06
    .wrapper
    -0.06
    например
    -0.06
    POSITIVE LOGITS
     QA
    0.07
    _KEEP
    0.07
     Romance
    0.07
    .fill
    0.07
     MOD
    0.07
    _CAST
    0.06
    Chars
    0.06
    stocks
    0.06
    テスト
    0.06
    퓶
    0.06
    Activations Density 0.083%

    No Known Activations