© 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. 15906
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms

    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
    ydd
    -0.08
    ByKey
    -0.07
    angkit
    -0.07
    人å±ħ
    -0.07
    ÑĦо
    -0.07
    ãĤĤãģ®ãģł
    -0.07
    bereit
    -0.07
    енÑĤи
    -0.07
    esia
    -0.07
    æĮīè§Ħå®ļ
    -0.07
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.09
    ween
    0.07
    èĢ¶
    0.07
    éģį
    0.07
    adesh
    0.07
    åĴĮæĶ¿æ²»
    0.07
    åĴĮæ³ķå¾ĭ
    0.07
    ukat
    0.07
    è¨ĢãģĨãģ¨
    0.07
    RTC
    0.07
    Activations Density 0.018%

    No Known Activations