© 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. 27-TRANSCODER-HP
    7. 9887
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     comps
    -0.28
     peptides
    -0.27
    åŃº
    -0.26
     instincts
    -0.26
    vals
    -0.25
     Budd
    -0.25
    æľ¬ç½ij
    -0.25
    äºĨåIJ§
    -0.24
    ambda
    -0.24
     registrations
    -0.24
    POSITIVE LOGITS
    idth
    0.36
    éĹªéĹª
    0.27
     conclusion
    0.27
    illion
    0.26
     fact
    0.26
    éķĩåħļå§Ķ
    0.26
    广åijĬæľįåĬ¡
    0.25
    æİ¥åĬĽ
    0.25
    itional
    0.25
    ä½ľèĢħæīĢæľī
    0.25
    Activations Density 0.005%

    No Known Activations