© 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. 27293
    Prev
    Next
    INDEX
    Explanations

    descriptive claim

    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
    etit
    -0.08
    大æ¦Ĥåľ¨
    -0.07
    主è¦ģéĴĪ对
    -0.07
    åºķèķ´
    -0.07
    elus
    -0.07
    ONO
    -0.07
    大æ¦Ĥæĺ¯
    -0.07
    sos
    -0.07
    ä¸įèĥ½è®©
    -0.07
    ÙĪاÙĦÙĬ
    -0.07
    POSITIVE LOGITS
     regardless
    0.12
     Regardless
    0.12
    ä¸įéĹ®
    0.11
    ä¸į管
    0.11
    Regardless
    0.11
     irrespective
    0.11
    Whatever
    0.11
     whatever
    0.10
     whichever
    0.10
    æĹłè®º
    0.10
    Activations Density 0.094%

    No Known Activations