© 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. 38851
    Prev
    Next
    INDEX
    Explanations

    UV rays and sunlight exposure

    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
     Сви
    -0.08
    ewater
    -0.07
    æµ
    -0.07
    ottom
    -0.07
     halls
    -0.07
    ogas
    -0.07
    çĵ¶é¢Ī
    -0.07
    ัà¸ģษà¹Į
    -0.07
    _RAM
    -0.07
    æijĨåľ¨
    -0.07
    POSITIVE LOGITS
    éĺ²æĻĴ
    0.14
    ç´«å¤ĸ线
    0.14
    缴å°Ħ
    0.13
     sunscreen
    0.13
     exposure
    0.12
    æļ´æĻĴ
    0.12
    æĻĴ
    0.12
    æĹ¥åħī
    0.12
     Exposure
    0.12
     sunlight
    0.11
    Activations Density 0.100%

    No Known Activations