© 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. 129859
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    fec
    -0.27
    åı¦
    -0.26
     enlist
    -0.24
    alion
    -0.24
    ugal
    -0.24
     rec
    -0.24
    __[
    -0.24
    ä¹Łä¼ļ
    -0.23
    ARC
    -0.23
     board
    -0.23
    POSITIVE LOGITS
    符
    0.28
    为主é¢ĺ
    0.28
     INCLUDED
    0.27
    åłª
    0.25
    Gem
    0.25
     kre
    0.24
    USED
    0.23
    æ£ģ
    0.23
     Rodrigo
    0.23
    (tok
    0.23
    Activations Density 16.162%

    No Known Activations