© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 50309
    Prev
    Next
    INDEX
    Explanations

    module

    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
    Negative Logits
    携手
    -0.08
    _NUM
    -0.07
     inaugural
    -0.07
     mantener
    -0.06
    ificio
    -0.06
    圯
    -0.06
    コンテン
    -0.06
    Restart
    -0.06
     assists
    -0.06
     historic
    -0.06
    POSITIVE LOGITS
    篼
    0.09
    生产厂家
    0.08
    foods
    0.08
     slee
    0.07
    表格
    0.07
    das
    0.07
    🕶
    0.07
    (Graph
    0.07
    dana
    0.07
    Ult
    0.07
    Activations Density 0.011%

    No Known Activations