© 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. 18236
    Prev
    Next
    INDEX
    Explanations

    units of distance or time

    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
    æĽ´èĥ½
    -0.30
    FTER
    -0.30
    æĽ´å¿«
    -0.28
    æ¡ħ
    -0.27
     æĽ´
    -0.27
    omore
    -0.26
    åIJİçļĦ
    -0.26
    æĽ´å¥½åľ°
    -0.26
    xfd
    -0.25
    ä¿¡æģ¯ç³»ç»Ł
    -0.24
    POSITIVE LOGITS
     out
    0.32
     off
    0.29
    cheme
    0.28
    outside
    0.28
    ress
    0.28
    out
    0.27
    apeut
    0.26
    çŃĸ
    0.26
     Second
    0.26
     outside
    0.25
    Activations Density 0.904%

    No Known Activations