© 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. 22378
    Prev
    Next
    INDEX
    Explanations

    light and electromagnetic radiation

    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
    åŁºç¡Ģ
    -0.08
    èįŁ
    -0.07
    为大家带æĿ¥
    -0.07
     tô
    -0.07
     баз
    -0.07
    ovy
    -0.07
    Expansion
    -0.07
    essed
    -0.07
    ConnectionFactory
    -0.07
     erweit
    -0.07
    POSITIVE LOGITS
     emitted
    0.10
     emission
    0.08
    æ³¢éķ¿
    0.07
     spectro
    0.07
    trap
    0.07
    èĥ½éĩı
    0.07
     wavelengths
    0.07
    -spec
    0.07
    åĪĨåŃIJçļĦ
    0.07
     molecule
    0.07
    Activations Density 0.005%

    No Known Activations