© 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. 142217
    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
    åħ¨æ°ij
    -0.27
     consecutive
    -0.26
    åĢĴåľ¨
    -0.25
    绪
    -0.24
    czy
    -0.24
    .makedirs
    -0.24
    追
    -0.24
    åŁĭ
    -0.24
    ÅĻ
    -0.24
    uhl
    -0.24
    POSITIVE LOGITS
    è®Ńç»ĥ
    0.25
     каÑĤал
    0.24
     newNode
    0.24
    allenge
    0.24
     Katherine
    0.24
    cision
    0.24
    rud
    0.23
    ä¸ĢåŃĹ
    0.23
     Retreat
    0.23
    rates
    0.23
    Activations Density 25.933%

    No Known Activations

    This feature has no known activations.