© 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. 64230
    Prev
    Next
    INDEX
    Explanations

    an

    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
    æ¼Ķ
    -0.30
    设æĸ½
    -0.28
    éĩįä¸Ń
    -0.26
    ç°¿
    -0.26
    广æĴŃ
    -0.25
    åħ¨äº§ä¸ļéĵ¾
    -0.24
    ÑĢиÑģ
    -0.24
    ç¢ij
    -0.24
    Clark
    -0.24
    æ¼Ķç»İ
    -0.24
    POSITIVE LOGITS
    [rand
    0.31
    PRETTY
    0.26
    ÐĴидео
    0.25
    æł¼å°Ķ
    0.25
    colo
    0.25
    PUR
    0.24
    [float
    0.24
    missive
    0.24
    ihan
    0.23
    icians
    0.23
    Activations Density 17.814%

    No Known Activations