© 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. 40610
    Prev
    Next
    INDEX
    Explanations

    representation theory

    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
    åıĮæĸ¹
    -0.07
     gate
    -0.07
    è¡¡
    -0.07
    交ä¼ļ
    -0.07
    _gate
    -0.07
    ÑĢиа
    -0.07
     absl
    -0.07
     parseFloat
    -0.07
     Fairfax
    -0.06
     Gate
    -0.06
    POSITIVE LOGITS
     Nil
    0.08
    Nil
    0.08
    æĭĶåĩº
    0.08
    (Level
    0.08
    第äºĮå¹´
    0.07
    nil
    0.07
    enerator
    0.07
    管çIJĨæ°´å¹³
    0.07
    æ£
    0.07
    äºĶ级
    0.07
    Activations Density 0.002%

    No Known Activations