© 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. 22952
    Prev
    Next
    INDEX
    Explanations

    division and remainder

    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
    еÑĪе
    -0.08
    åĽŀè¿ĩç¥ŀæĿ¥
    -0.08
    æģ¯çļĦ
    -0.08
    ਣ
    -0.07
    волÑĮ
    -0.07
     supervis
    -0.07
    äºĶèĬ±
    -0.07
     volg
    -0.07
    /reset
    -0.07
    sville
    -0.07
    POSITIVE LOGITS
    ono
    0.07
    åIJĮé¾Ħ
    0.06
    åĩºåħ·
    0.06
    æ¢
    0.06
    ongan
    0.06
    çļĭ
    0.06
    bab
    0.06
    iskus
    0.06
    éĥijéĩį声æĺİ
    0.06
    èĦij
    0.06
    Activations Density 0.004%

    No Known Activations