© 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. 63752
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text

    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
    æľŁ
    -0.27
    ients
    -0.26
    åį´è¢«
    -0.26
    åĨ³
    -0.25
    ..
    -0.25
    .builders
    -0.25
    pective
    -0.25
     reunion
    -0.24
     pInfo
    -0.24
    pec
    -0.24
    POSITIVE LOGITS
    yc
    0.28
    ñe
    0.28
    å¥ĸ项
    0.27
    øre
    0.26
    /Runtime
    0.26
    achs
    0.26
     thanks
    0.26
    /editor
    0.24
     MCP
    0.24
    注æĺİåĩºå¤Ħ
    0.24
    Activations Density 11.037%

    No Known Activations