© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37551
    Prev
    Next
    INDEX
    Explanations

    clarification and caveats

    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
    Negative Logits
    缴æİ¥æĪĸ
    -0.07
    äºĮåįģäºĶ
    -0.07
     Nem
    -0.07
    æ²ĥæĸ¯
    -0.07
     randomly
    -0.07
    รู
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.06
    ÏĮν
    -0.06
    otto
    -0.06
    åı·åı¬
    -0.06
    POSITIVE LOGITS
     caveat
    0.09
     clarification
    0.09
    以å¤ĩ
    0.08
    æ¾Ħæ¸ħ
    0.08
     fallback
    0.08
    å¤ĩéĢī
    0.08
    ä¸įæİĴéĻ¤
    0.08
    æĹłæ³ķ满足
    0.08
    ä¸įèĥ½æ»¡è¶³
    0.07
    (optional
    0.07
    Activations Density 0.023%

    No Known Activations