Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 163277
    Prev
    Next
    INDEX
    Explanations

    Medical abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĢij
    -0.28
     Born
    -0.26
    omics
    -0.26
    opus
    -0.26
     hatch
    -0.25
     ded
    -0.24
     (*)
    -0.24
    QUIRE
    -0.24
    asjon
    -0.24
    unday
    -0.23
    POSITIVE LOGITS
    åĽ´çĿĢ
    0.30
    érica
    0.28
    éĵ¶è¡Įåį¡
    0.25
    ä¸įéĻIJ
    0.25
    å°¤
    0.25
    西äºļ
    0.25
    \f
    0.24
    讽åĪº
    0.24
    ä¸įå°ı
    0.24
    迤
    0.24
    Activations Density 0.003%

    No Known Activations