© 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. 108034
    Prev
    Next
    INDEX
    Explanations

    reports or studies

    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
    ocha
    -0.31
    rowsers
    -0.29
    é¦ĸåħĪ
    -0.28
    depend
    -0.28
    ä¸ĢèĤ¡
    -0.27
    imizer
    -0.27
    <D
    -0.27
    empl
    -0.26
     Dep
    -0.26
    indr
    -0.26
    POSITIVE LOGITS
    iset
    0.29
    æĭīæĸ¯
    0.26
     underlying
    0.25
     signs
    0.25
    ë¦Ń
    0.25
    çĭį
    0.24
     ¶
    0.24
     onto
    0.24
    åIJİåĭ¤
    0.24
    ÃŃas
    0.24
    Activations Density 4.174%

    No Known Activations