© 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. 58606
    Prev
    Next
    INDEX
    Explanations

    Cambridge

    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
    eson
    -0.30
    åĴİ
    -0.27
     informative
    -0.26
    otre
    -0.26
    mes
    -0.26
    èµĽ
    -0.26
    estone
    -0.25
    oire
    -0.25
    lef
    -0.24
     Just
    -0.24
    POSITIVE LOGITS
    gable
    0.27
    -directed
    0.24
    çļĦåĬ¨ä½ľ
    0.24
     Yas
    0.24
    apses
    0.24
     rall
    0.24
    Sac
    0.24
    ãģªãģĦãģĵãģ¨
    0.24
    umps
    0.23
     Repeat
    0.23
    Activations Density 0.014%

    No Known Activations