© 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. 20-TRANSCODER-HP
    7. 129347
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĦı大
    -0.31
    æĺ¯ä¸Ģä½į
    -0.27
    redo
    -0.26
    Ð¡ÐŁ
    -0.26
     main
    -0.25
    æľīä¸Ģä½į
    -0.25
     Cre
    -0.25
    æ¢Ń
    -0.24
    èĬľ
    -0.24
    ÙĪجÙĩ
    -0.24
    POSITIVE LOGITS
     theirs
    0.29
    æĬĵ
    0.25
    檬
    0.24
    anz
    0.24
    <?,
    0.24
    nard
    0.23
    lesi
    0.23
    åĨħå¤ĸ
    0.23
    ographers
    0.23
    +'
    0.23
    Activations Density 5.443%

    No Known Activations