© 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. 96630
    Prev
    Next
    INDEX
    Explanations

    leader

    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
    kke
    -0.31
    ansson
    -0.29
    acy
    -0.25
    转载
    -0.25
     adip
    -0.25
    -browser
    -0.24
    æĢ§
    -0.24
    æĢ§åĴĮ
    -0.24
    atica
    -0.24
     addChild
    -0.24
    POSITIVE LOGITS
    é¢Ĩ导
    0.60
     leader
    0.57
     leadership
    0.55
    leader
    0.53
     Leader
    0.50
     leaders
    0.48
    leaders
    0.47
    éłĺå°İ
    0.46
    _leader
    0.46
     lÃŃder
    0.45
    Activations Density 0.892%

    No Known Activations