© 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. 38350
    Prev
    Next
    INDEX
    Explanations

    this is

    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
    è¿ĻäºĭåĦ¿
    -0.09
    äºĨè¿Ļ个
    -0.09
    è¿Ļ个æ¶Īæģ¯
    -0.08
    è¿Ļä¸ªé¡¹çĽ®
    -0.08
    æŃ¤èµ·
    -0.08
    åľ¨è¿Ļ
    -0.08
     ÙĦÙĩذا
    -0.08
    è¿Ļ款产åĵģ
    -0.08
    è¿Ļä¸ªä¸ľè¥¿
    -0.08
    è¿Ļ个äºĭæĥħ
    -0.08
    POSITIVE LOGITS
    ë¡ľìļ´
    0.07
    done
    0.07
     happens
    0.07
     done
    0.07
     happening
    0.07
    ern
    0.07
     happened
    0.06
     kerana
    0.06
     ÑģмоÑĤÑĢÑı
    0.06
    oft
    0.06
    Activations Density 0.133%

    No Known Activations