© 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. 108380
    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
     Pastor
    -0.27
    afil
    -0.26
    ë¦Ħ
    -0.24
    åĿ·
    -0.23
     aj
    -0.23
     unto
    -0.23
     nullptr
    -0.23
    ental
    -0.22
    ãģ«è¡Įãģı
    -0.22
    elpers
    -0.22
    POSITIVE LOGITS
    æĸ°äº¬
    0.28
    anca
    0.28
    olon
    0.27
    ä¹Łå¥½
    0.27
    åĴĮ社ä¼ļ
    0.27
    åĴĮ个人
    0.26
    ément
    0.25
     candid
    0.25
    é³Į
    0.24
    zac
    0.24
    Activations Density 0.286%

    No Known Activations

    This feature has no known activations.