© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64885
    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
    Negative Logits
    perimental
    -0.24
    çģ«çĦ°
    -0.24
     ire
    -0.24
    uncture
    -0.24
     prof
    -0.23
    Styles
    -0.23
    hydrate
    -0.23
    fff
    -0.23
    çīĪ
    -0.23
    uteur
    -0.23
    POSITIVE LOGITS
    rib
    0.27
    绿èī²éĢļéģĵ
    0.24
    å±Ĭ
    0.24
    åįģ大
    0.24
    .cv
    0.23
    èĿ¾
    0.23
    ALLERY
    0.23
    cession
    0.23
    riding
    0.23
    æ¶īæ¡Ī
    0.23
    Activations Density 4.876%

    No Known Activations

    This feature has no known activations.