© 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. 108240
    Prev
    Next
    INDEX
    Explanations

    Code and URLs

    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
    toFixed
    -0.28
    rzy
    -0.28
     Burl
    -0.25
     oneself
    -0.24
    incess
    -0.24
     leftover
    -0.24
    lard
    -0.24
    ombine
    -0.23
    æĻ¯è§Ĥ
    -0.23
    storeId
    -0.23
    POSITIVE LOGITS
    wise
    0.28
    æį»
    0.27
     ||č↵
    0.26
    wig
    0.25
    æ¡ĥèĬ±
    0.25
    ||(
    0.24
    æ¯įæł¡
    0.24
     gri
    0.24
    æij¸ç´¢
    0.24
    isse
    0.24
    Activations Density 7.339%

    No Known Activations