© 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. 63436
    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
    ton
    -0.27
    .squeeze
    -0.26
    bury
    -0.26
    ç²¾åįİ
    -0.25
    sure
    -0.25
    blast
    -0.25
    èµ°å»Ĭ
    -0.24
    oten
    -0.24
    Å¡t
    -0.24
    åī¥
    -0.24
    POSITIVE LOGITS
    ãĤ¿ãĥ«
    0.24
     clock
    0.24
    hcp
    0.23
    IVING
    0.23
    Pers
    0.23
    太å¤ļ
    0.23
    太å¤ļçļĦ
    0.22
    ãĥ³ãĥī
    0.22
    ä¸ŃåĽ½æ¢¦
    0.22
    roup
    0.22
    Activations Density 23.383%

    No Known Activations

    This feature has no known activations.