© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17142
    Prev
    Next
    INDEX
    Explanations

    HLA and MHC genes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    夯
    -0.08
    æľīæĪIJæķĪ
    -0.08
    å¾Ģå¤į
    -0.07
    ottage
    -0.07
    ungalow
    -0.07
    工夫
    -0.07
     Ibnu
    -0.07
     jet
    -0.06
    ä½ľæģ¯
    -0.06
    baugh
    -0.06
    POSITIVE LOGITS
    gen
    0.09
     genes
    0.09
     genetic
    0.08
    è¯¥ç³»ç»Ł
    0.08
     shield
    0.08
    éģĹä¼ł
    0.08
    /gen
    0.08
     Shield
    0.08
    éĵ²
    0.08
    æĬĹåİŁ
    0.08
    Activations Density 0.099%

    No Known Activations