© 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. 56389
    Prev
    Next
    INDEX
    Explanations

    minus, subtract, versus

    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
    éch
    -0.08
    estad
    -0.08
    oup
    -0.08
    éĽªçIJĥ
    -0.08
    ä¸įåĢĴ
    -0.08
     strcat
    -0.08
    ä¸įè¾ŀ
    -0.08
    ÑĤи
    -0.08
    ä¸įæķ£
    -0.07
    æ²Ļæ²³
    -0.07
    POSITIVE LOGITS
     minus
    0.14
    åĩıåİ»
    0.13
    minus
    0.09
    .subtract
    0.08
     vs
    0.08
    )-(
    0.08
    -minus
    0.08
     subtract
    0.08
     -
    0.08
     versus
    0.07
    Activations Density 0.014%

    No Known Activations