© 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. 22738
    Prev
    Next
    INDEX
    Explanations

    conjunctival, orbital, lash, eye

    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
    躯
    -0.08
    èħ¹åľ°
    -0.08
    罡
    -0.08
    èĦĬæ¢ģ
    -0.07
    åľŁåľ°åĪ©çĶ¨
    -0.07
    丰èĥ¸
    -0.07
    贴身
    -0.07
    _PCM
    -0.07
     Backbone
    -0.07
    é¼İ
    -0.07
    POSITIVE LOGITS
    éķľçīĩ
    0.12
     ocul
    0.12
     lenses
    0.12
    è§ĴèĨľ
    0.12
    çŀ³
    0.12
    çĿģå¼Ģ
    0.12
    è¿ijè§Ĩ
    0.12
    çľ¼ç§ij
    0.12
     eye
    0.11
     eyel
    0.11
    Activations Density 0.145%

    No Known Activations