© 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. 39634
    Prev
    Next
    INDEX
    Explanations

    arithmetic comparisons or operations

    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
    pery
    -0.08
     appunto
    -0.08
    èĢģèĢģå®ŀ
    -0.08
    áĥIJáĥĻ
    -0.08
    ëĵ¯
    -0.08
    çī©è¯Ń
    -0.08
    ibbon
    -0.07
    inkin
    -0.07
    Ñıн
    -0.07
    anje
    -0.07
    POSITIVE LOGITS
    0.07
    atas
    0.07
     ICT
    0.06
    à¸Ń
    0.06
    wab
    0.06
    jun
    0.06
    åŁİ
    0.06
    ç¦ı彩
    0.06
    çĶ¨æĿ¥
    0.06
    è§Ĩéĩİ
    0.06
    Activations Density 0.010%

    No Known Activations