© 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. 16771
    Prev
    Next
    INDEX
    Explanations

    mathematical 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
    ÙĤاض
    -0.07
    .Enum
    -0.07
    }//
    -0.06
    为åħ¨åĽ½
    -0.06
    amani
    -0.06
    æĺ¯åħ¨åĽ½
    -0.06
    ialis
    -0.06
     retur
    -0.06
    ushman
    -0.06
    olat
    -0.06
    POSITIVE LOGITS
    aden
    0.08
    assen
    0.07
    ä¹Ĵä¹ĵ
    0.07
    æļĤæĹł
    0.07
    jent
    0.07
    uren
    0.07
    ëĦ
    0.07
    ãĤīãģĹãģĦ
    0.07
    yun
    0.07
    ussen
    0.07
    Activations Density 0.002%

    No Known Activations