© 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. 142262
    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
    åıĺåİĭ
    -0.26
    ETHER
    -0.25
    款
    -0.25
    LEV
    -0.25
    UPER
    -0.25
    гал
    -0.25
    DMI
    -0.25
    ä½ıäºĨ
    -0.24
    为åĩĨ
    -0.24
    äºĮèĢħ
    -0.23
    POSITIVE LOGITS
    æĭ¥æĮ¤
    0.28
    -forward
    0.28
    ills
    0.25
    头æĿ¡
    0.25
    åħ¨å±Ģ
    0.25
    åıĪæĺ¯
    0.24
    éĥ½ä¼ļ
    0.24
    æľ¯è¯Ń
    0.24
     Mag
    0.24
    tek
    0.24
    Activations Density 1.849%

    No Known Activations

    This feature has no known activations.