© 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. 42442
    Prev
    Next
    INDEX
    Explanations

    asking questions about understanding

    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
    ascin
    -0.08
    æĽ´éĩįè¦ģçļĦ
    -0.08
    éĩįè¦ģçļĦäºĭæĥħ
    -0.08
    аÑĢи
    -0.08
    æĭ¥æľī丰å¯ĮçļĦ
    -0.08
    ä¸įåı¯èĥ½çļĦ
    -0.08
    enius
    -0.08
    å¥½ä¸ľè¥¿
    -0.08
    ä¹ŁæĽ´
    -0.08
    ]+'
    -0.08
    POSITIVE LOGITS
    ok
    0.08
    io
    0.07
    åĴĮåĨħ容
    0.07
    æĺ¯å¯¹çļĦ
    0.07
    okay
    0.06
    å°ļåı¯
    0.06
    dee
    0.06
    OK
    0.06
    è¿ĩçļĦ
    0.06
    gor
    0.06
    Activations Density 0.014%

    No Known Activations