© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9160
    Prev
    Next
    INDEX
    Explanations

    medical warnings

    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
    熟
    -0.07
     engulf
    -0.07
     exporting
    -0.07
    _SHADOW
    -0.06
     Palestin
    -0.06
    endforeach
    -0.06
     critiques
    -0.06
    二线城市
    -0.06
    采访时
    -0.06
     ];↵↵
    -0.06
    POSITIVE LOGITS
     nostra
    0.07
    なる
    0.07
     enlarge
    0.07
     DAY
    0.07
    moid
    0.07
     $_[
    0.07
     мм
    0.06
     bağlı
    0.06
    螭
    0.06
    𝐍
    0.06
    Activations Density 0.014%

    No Known Activations