© 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. 107220
    Prev
    Next
    INDEX
    Explanations

    function words

    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
    itz
    -0.27
    奢
    -0.26
    ãģĸ
    -0.26
    licht
    -0.25
     plagiar
    -0.25
    æĥ§
    -0.25
     copyrights
    -0.24
    quam
    -0.24
    kap
    -0.24
    ×Ļ×¢
    -0.23
    POSITIVE LOGITS
    åĴ¨è¯¢æľįåĬ¡
    0.29
    <!--[
    0.28
    rage
    0.26
    _TW
    0.26
    modifiable
    0.26
    çļĦæĵįä½ľ
    0.25
     Ara
    0.24
    æľ¬èº«å°±
    0.24
    æĶ¹éĿ©åıijå±ķ
    0.24
    èĮ±
    0.24
    Activations Density 5.745%

    No Known Activations