© 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. 18815
    Prev
    Next
    INDEX
    Explanations

    conclusion

    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
    æĩĤäºĨ
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    Ø´ÙĨ
    -0.06
    hint
    -0.06
    wak
    -0.06
    æĪĸå¤ļæĪĸå°ij
    -0.06
    åIJŁ
    -0.06
    ëĤ´ê¸°
    -0.06
    plied
    -0.06
    å¸Īé£İ
    -0.06
    POSITIVE LOGITS
    olim
    0.08
    å°±è¿Ļä¹Ī
    0.07
    æĸ°æ¨¡å¼ı
    0.07
    ç»ĵæŀľæĺ¾ç¤º
    0.07
    å®Įç»ĵ
    0.07
     заклÑİÑĩение
    0.07
    :result
    0.07
     conclu
    0.07
    AZE
    0.07
    OLI
    0.07
    Activations Density 0.003%

    No Known Activations