© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 106922
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĸ¹éĿ¢çļĦ
    -0.30
    mere
    -0.28
    <nav
    -0.28
    iesel
    -0.27
    çĶ¨è½¦
    -0.26
    为主é¢ĺçļĦ
    -0.26
    PerPixel
    -0.25
    virtual
    -0.25
    avia
    -0.25
    åĨ»ç»ĵ
    -0.24
    POSITIVE LOGITS
    edith
    0.25
    BF
    0.25
    tf
    0.24
     Shia
    0.24
    conc
    0.24
    ģını
    0.23
    clé
    0.23
     *}↵↵
    0.23
    示
    0.23
     воп
    0.23
    Activations Density 0.066%

    No Known Activations

    This feature has no known activations.