© 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. 38370
    Prev
    Next
    INDEX
    Explanations

    seems like, feels like

    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
    oke
    -0.07
    è¿Ľè¡ĮåŃ¦ä¹ł
    -0.06
     therein
    -0.06
    åİ»æĥ³
    -0.06
    upt
    -0.06
    zee
    -0.06
    æ´ĹéĿ¢
    -0.06
    á»ĵng
    -0.06
    羣å®ŀæĢ§
    -0.06
    soever
    -0.06
    POSITIVE LOGITS
    åĽŀäºĭ
    0.08
    icrosoft
    0.08
    ä¸ĢåĽŀäºĭ
    0.07
    æŀģäºĨ
    0.07
    a
    0.07
    ا
    0.07
    ofday
    0.07
    è¯ĿæĿ¥
    0.07
    atica
    0.07
    iw
    0.07
    Activations Density 0.036%

    No Known Activations