© 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. 37796
    Prev
    Next
    INDEX
    Explanations

    wavelengths and units (nm, cm)

    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
    elis
    -0.07
    æݨ
    -0.06
    º
    -0.06
    éĻĪå¿Ĺ
    -0.06
     боле
    -0.06
    ζη
    -0.06
    ISCO
    -0.05
    aton
    -0.05
    é¬ĵ
    -0.05
    ĺ
    -0.05
    POSITIVE LOGITS
    代ä¼ļ
    0.08
    欢è¿İåħī临
    0.08
     todd
    0.08
    åĮºåĴĮ
    0.08
    .googleapis
    0.08
    æĺ¾å¾Ĺå¾Ī
    0.08
    asthan
    0.07
    à¸Ľà¸£à¸°à¸Ĺาà¸Ļ
    0.07
    ioxide
    0.07
    emm
    0.07
    Activations Density 0.014%

    No Known Activations