© 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. 107673
    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
     tip
    -0.29
    çĽĬ
    -0.27
    echa
    -0.27
    åİŁ
    -0.26
     Minutes
    -0.26
    talk
    -0.25
     Inches
    -0.24
    åIJį为
    -0.24
    tip
    -0.24
    ellers
    -0.24
    POSITIVE LOGITS
    ypy
    0.27
    vasion
    0.26
    zhou
    0.25
    erot
    0.25
    éĿĴéĵľ
    0.24
    osaur
    0.24
    esco
    0.23
    enge
    0.23
    åŃIJ
    0.23
    æĹıèĩªæ²»åİ¿
    0.23
    Activations Density 1.237%

    No Known Activations

    This feature has no known activations.