© 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. 17458
    Prev
    Next
    INDEX
    Explanations

    specific instances and examples

    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
    оÑī
    -0.07
    μÎŃ
    -0.07
    +')
    -0.07
    ,',
    -0.07
    ç»´åħĭ
    -0.07
    ÙĤتص
    -0.07
    ICC
    -0.07
    bite
    -0.07
    htag
    -0.07
    åıĪä½ķ
    -0.06
    POSITIVE LOGITS
    示ä¾ĭ
    0.11
     example
    0.10
     sometimes
    0.09
    å¾Ģå¾Ģ
    0.09
     typical
    0.09
    æľīæŶ
    0.09
    example
    0.09
     often
    0.09
    éĢļ常
    0.09
    举ä¾ĭ
    0.08
    Activations Density 1.386%

    No Known Activations