© 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. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107062
    Prev
    Next
    INDEX
    Explanations

    disease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olarity
    -0.30
    é¥ķ
    -0.29
    ité
    -0.25
    idades
    -0.25
     cer
    -0.25
     пÑĢоиз
    -0.25
    '
    -0.24
    éĢĤçĶ¨äºİ
    -0.24
    idad
    -0.23
    è¢ĭ
    -0.23
    POSITIVE LOGITS
    arda
    0.31
     hete
    0.28
     Scrolls
    0.27
    ewhere
    0.26
    //=
    0.26
     slee
    0.25
     Bran
    0.25
    gross
    0.25
     Hof
    0.25
     KP
    0.24
    Activations Density 9.980%

    No Known Activations