© 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. 129934
    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
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.29
    hol
    -0.29
    allows
    -0.26
    çĹ´
    -0.26
    è¾ĵéĢģ
    -0.24
    Entering
    -0.24
    ä¹Łæ²¡ä»Ģä¹Ī
    -0.24
    ä¹Łå¸ĮæľĽ
    -0.24
    åħģ
    -0.23
    inki
    -0.23
    POSITIVE LOGITS
    ogle
    0.25
    @author
    0.25
     Barth
    0.25
    egree
    0.25
    fleet
    0.24
    NODE
    0.24
    vig
    0.24
    俱
    0.24
    imonials
    0.23
    Pairs
    0.23
    Activations Density 1.106%

    No Known Activations

    This feature has no known activations.