© 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. 141731
    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
    èĻŀ
    -0.27
    ä¸ĵå±ŀ
    -0.25
    åı¶
    -0.24
    owi
    -0.24
    Nm
    -0.24
    egot
    -0.24
    zig
    -0.24
    гÑĥ
    -0.24
    åıĺæĢģ
    -0.24
     XCT
    -0.23
    POSITIVE LOGITS
     dispos
    0.26
     badges
    0.26
     Radius
    0.26
     sched
    0.25
    odesk
    0.24
    -radius
    0.24
    æĺ¯ä½ł
    0.24
    Radius
    0.24
    athon
    0.24
    ë°ĺ
    0.24
    Activations Density 2.991%

    No Known Activations

    This feature has no known activations.