© 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. 63749
    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
    åıĮçľ¼
    -0.27
    袪
    -0.26
    ogue
    -0.25
     Jihad
    -0.25
    æīĵæ³ķ
    -0.23
    JOIN
    -0.23
    ä¿Ĺè¯Ŀ说
    -0.23
    duit
    -0.23
    etails
    -0.22
    itel
    -0.22
    POSITIVE LOGITS
     lacked
    0.28
    åĥ®
    0.27
     lacking
    0.27
    orsi
    0.25
    (Global
    0.25
    缺ä¹ı
    0.25
     lack
    0.25
    horn
    0.24
    werk
    0.24
    аÑĨион
    0.24
    Activations Density 8.723%

    No Known Activations

    This feature has no known activations.