© 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. 15262
    Prev
    Next
    INDEX
    Explanations

    only

    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
    ä»ħ次äºİ
    -0.08
     ëĭ¨ì§Ģ
    -0.08
    alu
    -0.08
    retty
    -0.07
    ãģ«ãĤĪãģı
    -0.07
    åħ¨ç³»
    -0.07
    主è¦ģæĺ¯éĢļè¿ĩ
    -0.07
    ä¸įéĻIJäºİ
    -0.07
     both
    -0.07
     simply
    -0.07
    POSITIVE LOGITS
    èĢĮå·²
    0.10
    æĺ¯ä¸įå¤ŁçļĦ
    0.09
    è¿Ļä¸Ģ个
    0.09
     thôi
    0.08
    èĢĮä¸Ķæĺ¯
    0.08
    åı¯è¨Ģ
    0.08
    iki
    0.07
    ãģĹãģĭãĤĤ
    0.07
    è¿ľè¿ľä¸įå¤Ł
    0.07
     تÙĤرÙĬب
    0.07
    Activations Density 0.289%

    No Known Activations