© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58830
    Prev
    Next
    INDEX
    Explanations

    arbitrary-precision arithmetic

    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
    åĽĽæµ·
    -0.09
    鸳鸯
    -0.08
    entra
    -0.08
    achel
    -0.07
     Fore
    -0.07
    ULLET
    -0.07
    agher
    -0.07
    InThe
    -0.07
    bury
    -0.07
    æ±ĩæĢ»è¡¨
    -0.07
    POSITIVE LOGITS
    è¶ħ大
    0.08
    è¶ħéķ¿
    0.08
    è¶ħä¹İ
    0.08
    odia
    0.08
     exponent
    0.07
     strings
    0.07
     circum
    0.07
     Strings
    0.07
    /string
    0.07
    istring
    0.07
    Activations Density 0.022%

    No Known Activations