© 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. 17101
    Prev
    Next
    INDEX
    Explanations

    state completed solved

    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
    åĢ¶
    -0.07
    _locator
    -0.06
     .
    -0.06
    åĽ½åĨħçļĦ
    -0.06
    ,.
    -0.06
    åĭ¾éĢī
    -0.06
    allis
    -0.06
    æĬ¥åijĬæĺ¾ç¤º
    -0.06
     sele
    -0.06
     perennial
    -0.06
    POSITIVE LOGITS
    æĪij们æŃ£åľ¨
    0.09
    è¿ĺæľª
    0.08
    æŃ£åľ¨
    0.08
    è¿ĺ没
    0.08
    æļĤæľª
    0.07
     Äijang
    0.07
    æŃ£åľ¨è¿Ľè¡Į
    0.07
    è¿ĺ没æľī
    0.07
    stash
    0.07
    åı¯éļıæŶ
    0.07
    Activations Density 0.056%

    No Known Activations