© 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. 130017
    Prev
    Next
    INDEX
    Explanations

    standard

    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
    æŁIJç§į
    -0.30
    iba
    -0.27
    æ¿ĢåĬ¨
    -0.26
    åŁŁ
    -0.25
    nger
    -0.24
    ssi
    -0.24
    èļ¯
    -0.24
    xo
    -0.23
    ABI
    -0.23
     Eig
    -0.23
    POSITIVE LOGITS
    cleanup
    0.30
    ricular
    0.27
    åIJĪä½ľ
    0.26
    ä½Ĩä»ĸ们
    0.26
    çļĦåIJĪä½ľ
    0.26
     conclusions
    0.25
     cleanup
    0.25
    (bp
    0.25
     goals
    0.24
    omic
    0.24
    Activations Density 17.196%

    No Known Activations