© 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. 31-TRANSCODER-HP
    7. 19478
    Prev
    Next
    INDEX
    Explanations

    Cr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     base
    -0.28
    ç§į
    -0.27
    ome
    -0.26
    è¡¥
    -0.26
    è¿Ľ
    -0.26
    edes
    -0.26
    amer
    -0.25
    .round
    -0.25
    ny
    -0.25
    org
    -0.25
    POSITIVE LOGITS
    ropic
    0.28
    æĤ±
    0.27
    èĬ±éĴ±
    0.26
    æľ¬èĥ½
    0.26
    ç«Ļéķ¿
    0.26
    arkers
    0.25
    åķ«
    0.24
    IGIN
    0.24
    ViewById
    0.23
    _finished
    0.23
    Activations Density 0.003%

    No Known Activations