© 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. 1653
    Prev
    Next
    INDEX
    Explanations

    nutritional content

    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
    iform
    -0.08
    _uniform
    -0.07
     rop
    -0.07
    jong
    -0.06
     operation
    -0.06
    å¾ģ
    -0.06
     Uniform
    -0.06
    åĨħéĥ¨ç®¡çIJĨ
    -0.06
     autoriz
    -0.06
    ä¸įåĩĨ
    -0.06
    POSITIVE LOGITS
    å¯ĮåIJ«
    0.10
    丰å¯ĮçļĦ
    0.09
    -rich
    0.09
    èĨ³é£Łçº¤ç»´
    0.08
     íĴįë¶Ģíķľ
    0.08
    è±IJå¯ĮçļĦ
    0.08
    åĴĮ丰å¯ĮçļĦ
    0.08
    è±Ĭå¯Į
    0.08
     aporte
    0.08
    fiber
    0.08
    Activations Density 0.059%

    No Known Activations