© 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. 31-TRANSCODER-HP
    7. 19760
    Prev
    Next
    INDEX
    Explanations

    Math equations and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    γ
    -0.44
     Theta
    -0.41
    Îĵ
    -0.40
    Ψ
    -0.39
     γ
    -0.39
    gamma
    -0.39
     Îĵ
    -0.38
    Φ
    -0.38
    Beta
    -0.38
     ε
    -0.38
    POSITIVE LOGITS
    éħ¸
    0.33
    idan
    0.26
    人为
    0.26
     $\
    0.25
    æĸij
    0.25
    imony
    0.25
    mar
    0.25
    $\
    0.25
    åħ¨åijĺ
    0.24
     Mines
    0.24
    Activations Density 7.263%

    No Known Activations