© 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. 65227
    Prev
    Next
    INDEX
    Explanations

    as followed by common words

    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
    agon
    -0.09
    ä½Ĩ并ä¸į
    -0.07
    å°½æľī
    -0.06
    imal
    -0.06
    ima
    -0.06
     Dak
    -0.06
     "
    -0.06
    oter
    -0.06
     sogenannte
    -0.06
    è·º
    -0.06
    POSITIVE LOGITS
    estes
    0.09
    ä¸Ģä¸ĭåIJ§
    0.08
    éľĢè¦ģåIJĮ
    0.08
    äºĪ
    0.08
    kung
    0.07
    oning
    0.07
    åijĹ
    0.07
    éĿĴéĿĴ
    0.07
    razia
    0.07
    æĭ³éģĵ
    0.07
    Activations Density 0.006%

    No Known Activations