© 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. 141064
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    åı«
    -0.31
    追究
    -0.28
    GPL
    -0.27
    EF
    -0.26
     Qin
    -0.25
    AVIS
    -0.25
     Shanghai
    -0.25
    hiba
    -0.25
    究
    -0.24
    究竣
    -0.24
    POSITIVE LOGITS
    èĮ¨
    0.28
    idl
    0.27
     centerX
    0.26
    ibrary
    0.26
    ongan
    0.25
    ioned
    0.25
    idUser
    0.25
    ç®Ń
    0.25
     copyrighted
    0.25
    UserCode
    0.25
    Activations Density 13.412%

    No Known Activations