© 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. 109451
    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
    kel
    -0.32
    uur
    -0.28
    åľ¨ä»ĸçļĦ
    -0.28
     geli
    -0.28
    åľ¨ä»ĸ
    -0.26
    omi
    -0.26
    ko
    -0.25
    _representation
    -0.25
     setName
    -0.25
    ä»ĸèĩªå·±
    -0.25
    POSITIVE LOGITS
    ä¸ĢèĦļ
    0.29
    åıĮèĦļ
    0.28
    åĵij
    0.27
    åį³å°Ĩ
    0.26
     Ashe
    0.25
    avascript
    0.25
    è½±
    0.24
    AGENT
    0.24
    ä¼¼
    0.24
    converted
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.