© 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. 17526
    Prev
    Next
    INDEX
    Explanations

    prime numbers, divisors, factors, algorithms

    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
    gén
    -0.08
    логи
    -0.08
    .hm
    -0.07
     onFocus
    -0.07
    èĵ¬
    -0.07
    ä¸Ģ鸣
    -0.07
    ÏĢοÏį
    -0.07
    elia
    -0.07
    ë¡Ģ
    -0.07
    西å¸Ĥ
    -0.07
    POSITIVE LOGITS
    udge
    0.07
     Verified
    0.07
     lifestyles
    0.07
    çļĦ家
    0.07
    pel
    0.06
     lend
    0.06
    å¾Ģå¤į
    0.06
     verified
    0.06
    scan
    0.06
    fahrer
    0.06
    Activations Density 0.003%

    No Known Activations