© 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. 88575
    Prev
    Next
    INDEX
    Explanations

    Chat or forum context

    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
    วาà¸ĩ
    -0.26
    å¢ŀåĬłåĢ¼
    -0.26
    ä¸ĬéĻIJ
    -0.24
    Observers
    -0.23
     won
    -0.23
     plans
    -0.23
    atég
    -0.23
    führ
    -0.23
    ç»Ń
    -0.23
    DAQ
    -0.23
    POSITIVE LOGITS
    åİ»åģļ
    0.29
    åįŁ
    0.26
    棱
    0.26
    è¿ĶåĽŀæIJľçĭIJ
    0.26
    Tonight
    0.25
    å¾Īå¤ļçݩ家
    0.24
    åģļä¸ĢäºĽ
    0.24
    åģļçļĦäºĭæĥħ
    0.24
    è¸ıä¸Ĭ
    0.24
    æĹ¢æľī
    0.23
    Activations Density 0.001%

    No Known Activations