© 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. 107371
    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
    oster
    -0.26
    DTV
    -0.25
    tte
    -0.24
     PIO
    -0.24
    æĹ¥æĬ¥ç¤¾
    -0.24
    nze
    -0.23
    鸷
    -0.23
    /engine
    -0.23
    .Checked
    -0.23
    æ¢
    -0.23
    POSITIVE LOGITS
    è´Ŀ壳
    0.27
     vez
    0.27
    åĪ«
    0.26
    æ°ij
    0.26
     Compass
    0.25
     Shelf
    0.25
    表çİ°
    0.25
     Outline
    0.24
     Libre
    0.24
    åį¿
    0.24
    Activations Density 1.844%

    No Known Activations

    This feature has no known activations.