© 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. 130340
    Prev
    Next
    INDEX
    Explanations

    scientific studies and health

    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
     ([[
    -0.27
    .slim
    -0.26
    Shock
    -0.25
    isel
    -0.24
    éĤĪ
    -0.24
    <k
    -0.24
    è¿ĻäºĽéĹ®é¢ĺ
    -0.24
     {.
    -0.24
    icts
    -0.24
    _Selected
    -0.23
    POSITIVE LOGITS
    lands
    0.31
    ç§į
    0.28
     Wyatt
    0.26
    nants
    0.25
     ===
    0.25
     aba
    0.24
    èĮĥæĸĩ
    0.23
     pla
    0.23
    天
    0.23
    é«ĺ
    0.23
    Activations Density 6.099%

    No Known Activations