© 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. 8791
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions 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
    -0.07
    æĸ¹ç¨ĭå¼ı
    -0.07
     calculated
    -0.06
    å¼ıä¸Ń
    -0.06
    ema
    -0.06
     standby
    -0.06
     scientifically
    -0.06
    常éĩı
    -0.06
    -0.06
     contingency
    -0.06
    POSITIVE LOGITS
    endom
    0.10
    EGA
    0.09
     specializing
    0.09
    Mappings
    0.09
    adge
    0.09
     nicer
    0.09
     functor
    0.09
    restriction
    0.09
     constructions
    0.09
    åı¯æ¢¦
    0.09
    Activations Density 0.065%

    No Known Activations