© 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. 55461
    Prev
    Next
    INDEX
    Explanations

    math and calculations

    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
    èijĨ
    -0.09
    磼
    -0.09
    éĩij森
    -0.09
    onaut
    -0.08
    _restrict
    -0.08
    icato
    -0.08
    å¥½ä¹łæĥ¯
    -0.08
    .loaded
    -0.08
    åİĨéĻ©
    -0.08
    issy
    -0.08
    POSITIVE LOGITS
     calculations
    0.14
     math
    0.14
     calculation
    0.13
    æķ°åѦ
    0.13
     mathematical
    0.13
     matem
    0.13
     matemat
    0.12
    计ç®Ĺ
    0.12
    计ç®Ĺåħ¬å¼ı
    0.12
     mathematics
    0.11
    Activations Density 0.595%

    No Known Activations