© 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. 39484
    Prev
    Next
    INDEX
    Explanations

    Mendelian genetics

    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
    renc
    -0.08
    æĶ¹éĢłå·¥ç¨ĭ
    -0.08
     Déf
    -0.07
    ια
    -0.07
    opensource
    -0.07
    EXEC
    -0.07
     пÑĢÑĥ
    -0.07
    >Last
    -0.07
     writeTo
    -0.07
    ambient
    -0.07
    POSITIVE LOGITS
     genetics
    0.11
     Genetics
    0.10
    åŁºåĽł
    0.09
    éģĹä¼ł
    0.09
     genetic
    0.09
    å®ļå¾ĭ
    0.08
     Mend
    0.08
     gene
    0.08
     patterns
    0.08
    åŁºåĽłçļĦ
    0.08
    Activations Density 0.011%

    No Known Activations