© 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. 7912
    Prev
    Next
    INDEX
    Explanations

    various

    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
    aab
    -0.29
    以èĩ³äºİ
    -0.27
     главное
    -0.24
    ines
    -0.23
    çĴĺ
    -0.23
    -ln
    -0.23
    atura
    -0.23
    ãĤ¯ãĥĪ
    -0.23
    ç¦Ģ
    -0.23
    avors
    -0.23
    POSITIVE LOGITS
     various
    1.05
    åIJĦç§į
    0.94
     Various
    0.84
    Various
    0.78
     several
    0.77
    çļĦåIJĦç§į
    0.73
    åIJĦ種
    0.71
    åIJĦç±»
    0.71
    ä¸ĢäºĽ
    0.65
    åIJĦç§įåIJĦæł·
    0.62
    Activations Density 0.012%

    No Known Activations