© 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. 11361
    Prev
    Next
    INDEX
    Explanations

    perihelion

    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
    åĪ¶çļĦ
    -0.07
    齡
    -0.07
    æľ¬è´¨
    -0.07
    åĴĮçIJĨ解
    -0.06
     Sense
    -0.06
     sense
    -0.06
     hor
    -0.06
    åĪ¶
    -0.06
    åIJİæĦŁ
    -0.06
    elman
    -0.06
    POSITIVE LOGITS
    åİĨ
    0.08
    æľºæ¢°è®¾è®¡
    0.07
    imum
    0.07
    çĭ
    0.07
    hofer
    0.07
     biograf
    0.07
    quÃŃ
    0.07
    çļĦ详ç»Ĩ
    0.07
     recur
    0.07
    ját
    0.07
    Activations Density 0.003%

    No Known Activations