© 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. 30653
    Prev
    Next
    INDEX
    Explanations

    corporate or client mentions

    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
    ä¹ĭéĹ´çļĦèģĶç³»
    -0.06
    пÑĥÑĤ
    -0.06
     Ø´Ùĩ
    -0.06
    就容æĺĵ
    -0.06
    æĪijå°±ä¼ļ
    -0.06
    ÑİÑĢ
    -0.06
    å®ĥè¿ĺ
    -0.06
    umed
    -0.06
    åħ¶èº«
    -0.06
    fino
    -0.06
    POSITIVE LOGITS
    ä¸İæѤ
    0.11
    对ä¸Ĭè¿°
    0.10
    ingleton
    0.08
    ä¸İ该
    0.08
    ä¸İå°ı
    0.08
    .tem
    0.08
    ä¸İä¹ĭ
    0.07
    ä¸İä»ĸ们
    0.07
    _lua
    0.07
    egers
    0.07
    Activations Density 0.079%

    No Known Activations