© 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. 63780
    Prev
    Next
    INDEX
    Explanations

    large

    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
    hon
    -0.27
    atif
    -0.27
    å¼ĤæĢ§
    -0.26
    å¹¼ç¨ļ
    -0.26
    eslint
    -0.26
     Ther
    -0.24
    æ¯ķ
    -0.24
    å¾Īæĺİæĺ¾
    -0.24
    Paren
    -0.24
     gegenüber
    -0.24
    POSITIVE LOGITS
    /sub
    0.28
     snake
    0.26
     amount
    0.26
     amounts
    0.25
     strength
    0.25
    úng
    0.25
    çݯå¢ĥä¸ĭ
    0.25
    aus
    0.24
    dens
    0.24
     people
    0.23
    Activations Density 23.154%

    No Known Activations