© 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. 56792
    Prev
    Next
    INDEX
    Explanations

    this is that

    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
    éĢļ常æĥħåĨµä¸ĭ
    -0.08
    åľ¨è¿Ļç§į
    -0.08
    ,module
    -0.07
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    -0.07
    æľ¬èº«å°±æĺ¯
    -0.07
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    -0.07
    åľ¨è¿Ļ个
    -0.07
    è¿Ļ个æŶåĢĻ
    -0.07
    ä¹ĭåīįåľ¨
    -0.07
    åľ¨è¿Ļ个æŶåĢĻ
    -0.07
    POSITIVE LOGITS
    表çݰ为
    0.10
    :nth
    0.08
     equivalent
    0.07
    heck
    0.07
    adera
    0.07
     translates
    0.06
    å½ĵä¹ĭæĹłæĦ§
    0.06
    åıĺæĪIJäºĨä¸Ģ个
    0.06
    ente
    0.06
    ä¼ļåıĺæĪIJ
    0.06
    Activations Density 0.335%

    No Known Activations