© 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. 141625
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
    è¿Ļåı¥è¯Ŀ
    -0.30
    è¿Ļç§į
    -0.27
    eft
    -0.26
    ignal
    -0.24
    á»ŀ
    -0.24
    è¿Ļè¯Ŀ
    -0.24
     USERNAME
    -0.24
    åIJ¬ä¼Ĺ
    -0.24
     pose
    -0.23
    åªĴ
    -0.23
    POSITIVE LOGITS
    ExecutionContext
    0.29
     firing
    0.28
     Seller
    0.26
    à¹Ĥà¸Ļ
    0.26
    pu
    0.26
    å¨
    0.25
    [âĢ¦
    0.25
    ardy
    0.25
    èĢĮæĪIJ
    0.25
    æķ°é¢Ŀ
    0.24
    Activations Density 3.863%

    No Known Activations