© 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. 130518
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æľīæĿ¡ä»¶çļĦ
    -0.35
    ãģ²ãģ¨
    -0.26
    indrome
    -0.26
    ypy
    -0.24
    å¾Ĺ
    -0.24
    ãģĸ
    -0.24
    teenth
    -0.23
     loro
    -0.23
    [*
    -0.23
    è¿Ļä¹Ī说
    -0.23
    POSITIVE LOGITS
     Ont
    0.26
     Upload
    0.25
    第ä¸Ģ天
    0.24
    /Linux
    0.23
    _uploaded
    0.23
     startPos
    0.23
    (Method
    0.23
     responseBody
    0.23
     horm
    0.23
     newPos
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.