© 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. 29018
    Prev
    Next
    INDEX
    Explanations

    Code and formulas

    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
    体质
    -0.07
     Kob
    -0.07
     Mitgli
    -0.07
    浐
    -0.07
    使用者或
    -0.07
     квар
    -0.07
    .changed
    -0.07
     penny
    -0.06
    /ca
    -0.06
     rq
    -0.06
    POSITIVE LOGITS
    过去了
    0.08
    翳
    0.07
    Room
    0.07
     thought
    0.07
     autos
    0.07
    辟
    0.07
    约谈
    0.07
    弹
    0.06
    碌
    0.06
    ограф
    0.06
    Activations Density 0.078%

    No Known Activations