© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25495
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    举ä¾ĭ
    -0.29
    .TryParse
    -0.28
    oose
    -0.26
    çŁŃ线
    -0.25
    opard
    -0.25
    æľĢæĸ°çļĦ
    -0.25
    èĤ¡
    -0.24
    igar
    -0.24
    Ratio
    -0.24
    ist
    -0.24
    POSITIVE LOGITS
     kilometers
    0.28
     goof
    0.27
    itr
    0.25
     pass
    0.25
     kilometres
    0.25
    lei
    0.24
    åįĥç±³
    0.24
    太å°ij
    0.24
     cent
    0.24
    åħ¬æĸ¤
    0.24
    Activations Density 0.006%

    No Known Activations