© 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. 78301
    Prev
    Next
    INDEX
    Explanations

    childhood education

    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
    介入
    -0.07
    养殖
    -0.07
     onHide
    -0.07
     contaminated
    -0.07
     nhạc
    -0.07
    ,’’
    -0.07
    UN
    -0.07
    杀菌
    -0.06
    结合
    -0.06
     And
    -0.06
    POSITIVE LOGITS
     oleh
    0.09
     holes
    0.07
     xuyên
    0.07
    מקצוע
    0.07
     Believe
    0.07
     ROCK
    0.07
    蛋白质
    0.06
     Scala
    0.06
    singleton
    0.06
     прос
    0.06
    Activations Density 0.028%

    No Known Activations