© 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. 58294
    Prev
    Next
    INDEX
    Explanations

    features and scenarios

    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
     Britann
    -0.07
    èijĹåIJįçļĦ
    -0.07
     mens
    -0.07
     mirac
    -0.07
    æŃ£ç¡®çļĦ
    -0.07
    åĭĴæĸ¯
    -0.07
    ä¸ĢèĪ¬
    -0.07
     infinit
    -0.06
    çĶ¨äºİ
    -0.06
    æĤī
    -0.06
    POSITIVE LOGITS
    åģıå¼±
    0.09
    elleicht
    0.09
    çīĪæĿĥä¸İåħį责声æĺİ
    0.08
    æľ¬ç½ij转载
    0.08
     destabil
    0.08
    注éĶĢå¤ĩæ¡Ī
    0.08
    æĸ¹æ³ķ论
    0.08
    åı¯æľĽ
    0.08
    å¹ħ
    0.08
    游åĪĥæľīä½Ļ
    0.08
    Activations Density 0.009%

    No Known Activations