© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38288
    Prev
    Next
    INDEX
    Explanations

    prime, integer, number

    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
    ÙĨØ©
    -0.09
    æĸ°åĬłåĿ¡
    -0.08
    elho
    -0.08
    è¿ĩ度çļĦ
    -0.08
    chst
    -0.08
    bara
    -0.08
    æĭŃ缮
    -0.07
    æĸ°ç¤¾
    -0.07
    shot
    -0.07
    SHOT
    -0.07
    POSITIVE LOGITS
     integers
    0.12
     numbers
    0.10
     integer
    0.09
    æķ´æķ°
    0.09
     Zahlen
    0.08
    numbers
    0.08
    æŃ£åĢ¼
    0.07
     non
    0.07
    éĿŀ
    0.07
    æķ°åĢ¼
    0.07
    Activations Density 0.030%

    No Known Activations