© 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. 64274
    Prev
    Next
    INDEX
    Explanations

    discussion, guide, tips, compilation

    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
    çŁ¥éģĵåIJĹ
    -0.09
    订éĺħä¸ĵæłı
    -0.09
    nesia
    -0.09
    åıij表讨论
    -0.08
    #echo
    -0.08
    ä¸ĭè½½æĬ¥åijĬ
    -0.08
    [".
    -0.08
    åĽ¾çīĩæĪĸ
    -0.08
    niest
    -0.08
    .addValue
    -0.08
    POSITIVE LOGITS
     illustrates
    0.07
     recent
    0.06
    *
    0.06
     together
    0.06
    æĹ¢æľī
    0.06
     outlines
    0.06
     below
    0.06
     comp
    0.06
    çļĦæł¸å¿ĥ
    0.06
    under
    0.06
    Activations Density 0.008%

    No Known Activations