© 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. 22-TRANSCODER-HP
    7. 88361
    Prev
    Next
    INDEX
    Explanations

    "/**" start of comments (in code)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    樵
    -0.31
     Trades
    -0.25
    Aware
    -0.25
    ç»ıæµİæĬĢæľ¯
    -0.24
    idas
    -0.24
    æĮijéĢī
    -0.24
    ÑĢид
    -0.24
     oneself
    -0.24
    æľīä¸įåIJĮçļĦ
    -0.24
    æ£ĺ
    -0.23
    POSITIVE LOGITS
    åĤį
    0.26
    ड
    0.24
    åĬĦ
    0.24
    天èĬ±æĿ¿
    0.24
     exc
    0.24
    ents
    0.24
     prof
    0.23
    _optimizer
    0.23
    å§ĭç»Īä¿ĿæĮģ
    0.23
     recently
    0.23
    Activations Density 0.019%

    No Known Activations