© 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. 20-TRANSCODER-HP
    7. 141651
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    roma
    -0.27
    hon
    -0.25
     dr
    -0.24
    _pd
    -0.24
    .Dom
    -0.24
    æij¸ç´¢
    -0.24
     mut
    -0.24
    ãĬ
    -0.23
    è£ĺ
    -0.23
    åİ»çľĭ
    -0.23
    POSITIVE LOGITS
    æĿĨ
    0.29
    ä¾Ľ
    0.28
    uxe
    0.25
    æĪĸå¤ļ
    0.25
    åį·
    0.24
    зал
    0.24
    .deepcopy
    0.24
    æ¸ħåįķ
    0.24
    /Branch
    0.24
     Koh
    0.24
    Activations Density 9.404%

    No Known Activations

    This feature has no known activations.