© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7277
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æİ¥åĬĽ
    -0.26
    åı®åĺ±
    -0.26
    aters
    -0.26
    åŃ©åŃIJ
    -0.25
    icture
    -0.24
    責任
    -0.24
    IFO
    -0.24
     Casc
    -0.24
     agreed
    -0.23
    éĿł
    -0.23
    POSITIVE LOGITS
    æķĿ
    0.26
    ombre
    0.26
    太å°ij
    0.25
    éģĹå¿ĺ
    0.25
    usch
    0.24
    ç²¾
    0.24
    åľ¨ä»ĸçļĦ
    0.24
     digs
    0.24
    åĪ¨
    0.24
    éĦĻ
    0.24
    Activations Density 0.339%

    No Known Activations

    This feature has no known activations.