© 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. 20931
    Prev
    Next
    INDEX
    Explanations

    modulo arithmetic and cryptography

    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
    æĸŃè£Ĥ
    -0.06
     torne
    -0.06
     Nest
    -0.06
    æŀ¯
    -0.06
    ibrary
    -0.06
     Tun
    -0.06
    ä¼ģ稳
    -0.06
     Contemporary
    -0.06
    -font
    -0.06
    orrh
    -0.06
    POSITIVE LOGITS
     modulo
    0.13
    modulo
    0.10
    bacher
    0.09
     permutations
    0.08
    empel
    0.08
    gcd
    0.08
     Cipher
    0.08
    Cipher
    0.08
     hashing
    0.08
     encrypt
    0.08
    Activations Density 0.007%

    No Known Activations