© 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. 107151
    Prev
    Next
    INDEX
    Explanations

    Ban

    np_max-act-logits · gemini-2.0-flash
    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
    ä¸į足
    -0.26
    ến
    -0.25
    ESP
    -0.25
     defined
    -0.25
    rib
    -0.24
     (;;
    -0.24
    /profile
    -0.24
    åij¨åĽ´çļĦ
    -0.23
    æİī
    -0.23
    Selected
    -0.23
    POSITIVE LOGITS
    sites
    0.27
    çľ¼è¢ĭ
    0.26
     PROT
    0.24
    pac
    0.24
    å¢Ļå£ģ
    0.24
    izzo
    0.24
    orny
    0.23
    羣çļ®
    0.23
    rets
    0.23
     absorbs
    0.23
    Activations Density 0.095%

    No Known Activations