© 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. 48266
    Prev
    Next
    INDEX
    Explanations

    modular arithmetic and operations

    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
    Ïģγο
    -0.08
    å·Ŀèıľ
    -0.07
    ursor
    -0.07
    æİĸ
    -0.07
    èĬ±èIJ½
    -0.07
    ä¸Ģå¸Ĩ
    -0.07
    åīĸ
    -0.07
    èĢ½
    -0.07
    çĢ¬
    -0.07
     Viale
    -0.07
    POSITIVE LOGITS
     arithmetic
    0.08
    åľ°éģĵ
    0.08
    åĽŀæķ°
    0.08
    gcd
    0.07
    éĽ
    0.07
    adecimal
    0.07
     notation
    0.07
    /bus
    0.07
     modulo
    0.07
    awi
    0.07
    Activations Density 0.015%

    No Known Activations