© 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. 9860
    Prev
    Next
    INDEX
    Explanations

    les

    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
    æĵįä½ľ
    -0.63
    示èĮĥ
    -0.60
    çļĦæĵįä½ľ
    -0.59
    æ¼Ķ示
    -0.59
    æĬĢèĥ½
    -0.54
    åĬ¨æīĭ
    -0.51
     demonstrations
    -0.51
     demonstration
    -0.50
    æĬĢèīº
    -0.47
    çļĦåĬ¨ä½ľ
    -0.45
    POSITIVE LOGITS
    @class
    0.29
    贯彻
    0.28
     Contract
    0.28
     contract
    0.27
    åIJĪåIJĮ
    0.25
     talking
    0.25
     Contracts
    0.24
    ergarten
    0.24
    æļ´éĽ¨
    0.24
     lãnh
    0.24
    Activations Density 0.002%

    No Known Activations