© 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. 106955
    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
    Reviewed
    -0.26
    fall
    -0.24
    .nih
    -0.24
    ë²Į
    -0.24
     ...
    -0.24
    æħ¨
    -0.24
    zeit
    -0.23
     Bender
    -0.23
    é»ĦçŁ³
    -0.23
     department
    -0.23
    POSITIVE LOGITS
    ourn
    0.28
    æĺ¯çĶ¨æĿ¥
    0.27
    沿线
    0.27
    ãģĭãģĦ
    0.27
    æĪ¶
    0.25
    çıĪ
    0.25
    为主é¢ĺ
    0.24
    kad
    0.24
    ature
    0.24
    第åħŃå±Ĭ
    0.24
    Activations Density 0.974%

    No Known Activations

    This feature has no known activations.