© 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. 21879
    Prev
    Next
    INDEX
    Explanations

    common divisor or factor

    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
    æ§Ľ
    -0.08
    顺é£İ
    -0.07
    enek
    -0.06
    ÑģÑĤила
    -0.06
     Gro
    -0.06
    æ·
    -0.06
    ä¼Ĺ
    -0.06
    utton
    -0.06
     gro
    -0.06
     NVIC
    -0.06
    POSITIVE LOGITS
    åı¯èĥ½æĺ¯
    0.08
    ÄĻd
    0.08
     likely
    0.08
     Aper
    0.08
    åIJĽå®ī
    0.07
    likely
    0.07
    ¤íĭ
    0.07
    ottage
    0.07
    posix
    0.07
    çĸijä¼¼
    0.07
    Activations Density 0.004%

    No Known Activations