© 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. 19-RESID-POST-AA
    11. 71036
    Prev
    Next
    INDEX
    Explanations

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tır
    -0.07
    placed
    -0.07
     journée
    -0.07
    荣获
    -0.07
    示范区
    -0.07
    эр
    -0.06
     בגין
    -0.06
    げ
    -0.06
    opsy
    -0.06
    働く
    -0.06
    POSITIVE LOGITS
    舥
    0.08
    0.08
    基础
    0.08
     planetary
    0.07
    主机
    0.07
     parallel
    0.06
     strSql
    0.06
     extensively
    0.06
    �
    0.06
     engaged
    0.06
    Activations Density 0.002%

    No Known Activations