© 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. 57395
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and solutions

    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
    à¸ģลà¸ĩ
    -0.07
    arine
    -0.07
    ве
    -0.07
    éĢ¢
    -0.06
     unless
    -0.06
     uncomment
    -0.06
    æĪijè·Ł
    -0.06
     until
    -0.06
    +"&
    -0.06
    oyer
    -0.06
    POSITIVE LOGITS
    ä¸įèĻļ
    0.08
    ncio
    0.08
    ëĵľëĬĶ
    0.08
     =
    0.08
    ittest
    0.07
    nö
    0.07
    ede
    0.07
    /jav
    0.07
    _GPU
    0.07
    ÃŃso
    0.07
    Activations Density 0.018%

    No Known Activations