© 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. 107462
    Prev
    Next
    INDEX
    Explanations

    business

    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
    tif
    -0.26
    cea
    -0.26
    TAB
    -0.26
    PageRoute
    -0.25
    latable
    -0.24
    uja
    -0.24
     toJson
    -0.24
    rous
    -0.24
    atto
    -0.23
    utos
    -0.23
    POSITIVE LOGITS
     both
    0.29
    æĹ¢
    0.28
     haunt
    0.28
     Mag
    0.27
    mland
    0.25
    æĹ¢è¦ģ
    0.25
     transc
    0.25
    马åħĭ
    0.25
    尺度
    0.25
    å¸Ń
    0.24
    Activations Density 15.625%

    No Known Activations