© 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. 107216
    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
    éĢıè¿ĩ
    -0.27
    pivot
    -0.27
    lut
    -0.26
    .REG
    -0.26
    grey
    -0.26
    (gray
    -0.26
    iolet
    -0.25
    RuleContext
    -0.25
    mis
    -0.25
    assi
    -0.25
    POSITIVE LOGITS
    (nil
    0.28
     Nil
    0.26
     CALLBACK
    0.26
     nil
    0.26
    ä¸Ģç¬Ķ
    0.25
    =nil
    0.24
     reels
    0.24
    Nil
    0.24
    åģ¥
    0.24
    人éĢī
    0.23
    Activations Density 9.657%

    No Known Activations

    This feature has no known activations.