© 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. 88291
    Prev
    Next
    INDEX
    Explanations

    popular

    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
    å¤ļä½į
    -0.30
    é¢ijç¹ģ
    -0.30
     nombreux
    -0.29
    大è§Ħ模
    -0.28
    大éĩı
    -0.28
    å¤ļ次
    -0.26
    座æ¤ħ
    -0.26
    ç»ıéªĮ丰å¯Į
    -0.26
    æ¤ħ
    -0.26
    >Description
    -0.26
    POSITIVE LOGITS
     among
    0.30
    among
    0.29
    ä¸ĢæŶ
    0.28
     Among
    0.28
    æ¼ī
    0.26
    apy
    0.26
     ÑģÑĢеди
    0.26
    度è¿ĩ
    0.26
    pir
    0.25
    occ
    0.25
    Activations Density 0.111%

    No Known Activations