© 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. 57451
    Prev
    Next
    INDEX
    Explanations

    some [noun]

    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
    /of
    -0.08
    æīĢå±ŀåĪĨç±»
    -0.08
     respectivas
    -0.08
    ätt
    -0.08
    innen
    -0.08
    arcer
    -0.07
    çļĦäºĨ
    -0.07
    ugd
    -0.07
    rade
    -0.07
    åĭĴæĸ¯
    -0.07
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.12
    çłĶ究表æĺİ
    0.10
    èµĦæĸĻæĺ¾ç¤º
    0.09
    æĥħæ³ģä¸ĭ
    0.09
    æĻĤåĢĻ
    0.08
    æŶåĢĻ
    0.08
    人åĸľæ¬¢
    0.08
    ä¸ĵ家认为
    0.08
    body
    0.07
    åħ¬åı¸ä»¥
    0.07
    Activations Density 0.176%

    No Known Activations