© 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. 107380
    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
     perse
    -0.30
    ç»ıåħ¸çļĦ
    -0.28
    mond
    -0.28
    åħ¬çĽĬ
    -0.27
    pets
    -0.26
    ä¸ĵä¸ļçļĦ
    -0.26
    +xml
    -0.25
    undra
    -0.25
    pet
    -0.25
    tap
    -0.25
    POSITIVE LOGITS
    ccess
    0.25
    .HasValue
    0.25
    yme
    0.23
    charted
    0.23
    azzo
    0.23
     fig
    0.23
     oct
    0.23
    licht
    0.23
     newData
    0.23
    azzi
    0.23
    Activations Density 0.493%

    No Known Activations

    This feature has no known activations.