© 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. 23-TRANSCODER-HP
    7. 25135
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĻļ
    -0.30
    禺
    -0.29
    logan
    -0.27
     late
    -0.27
     krist
    -0.27
     luc
    -0.26
    _sz
    -0.26
    .buf
    -0.25
    icz
    -0.24
     Raz
    -0.23
    POSITIVE LOGITS
    ’all
    0.28
    aju
    0.28
    çļĦ认åı¯
    0.28
     Wich
    0.27
    åı¯éĢļè¿ĩ
    0.26
    æĺ¯åIJ¦ä¼ļ
    0.25
    .copyWith
    0.24
    lever
    0.24
    éĢļçŁ¥ä¹¦
    0.24
    ä¸įåı¯æĢĿè®®
    0.24
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.