© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95733
    Prev
    Next
    INDEX
    Explanations

    official titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¡è¯Ħ论
    -0.25
    %c
    -0.25
     weighted
    -0.25
    å¾ģæĪĺ
    -0.25
    roit
    -0.25
    amientos
    -0.25
    æĥij
    -0.24
    èµŀåIJĮ
    -0.24
    åŀ¢
    -0.24
    yük
    -0.24
    POSITIVE LOGITS
    missions
    0.26
    ifter
    0.25
    Aff
    0.25
    FER
    0.25
    åĽ½éĻħæľºåľº
    0.25
    _GT
    0.24
    äºĭ
    0.24
    evin
    0.24
    SX
    0.24
     sÅĤow
    0.24
    Activations Density 0.884%

    No Known Activations