© 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. 10546
    Prev
    Next
    INDEX
    Explanations

    focus spot

    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
    pector
    -0.08
    phu
    -0.08
    ä¹ĭé£İ
    -0.07
    orio
    -0.07
    _INTERVAL
    -0.07
    acun
    -0.07
    áºŃt
    -0.07
    éĢļåĪĻ
    -0.07
     cad
    -0.07
     PIE
    -0.07
    POSITIVE LOGITS
    缴å¾Ħ
    0.08
     Gaussian
    0.08
    æī©å¤§
    0.08
    尺寸
    0.08
     gaussian
    0.08
    åij¨åĽ´
    0.08
    spot
    0.07
     اÙĦشع
    0.07
    size
    0.07
     footprint
    0.07
    Activations Density 0.024%

    No Known Activations