© 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. 32071
    Prev
    Next
    INDEX
    Explanations

    file names or specific items

    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
     vend
    -0.07
    stel
    -0.07
    äºĨä¸Ģé¢Ĺ
    -0.07
    zeb
    -0.07
    vend
    -0.07
    óng
    -0.07
    ç«¥
    -0.06
    ök
    -0.06
    天å¤ĸ
    -0.06
    omt
    -0.06
    POSITIVE LOGITS
    ë§Īëĭ¤
    0.12
    ãģĶãģ¨ãģ«
    0.10
    ä¸Ģ个个
    0.09
    ë³Ħë¡ľ
    0.09
    åľ¨æ¯ı个
    0.09
    æ¯ı家
    0.09
    æ¯ıä¸Ģ件
    0.08
    æ¯ı次
    0.08
    æ¯ıä¸Ģ次
    0.08
    æ¯ı次éĥ½
    0.08
    Activations Density 0.367%

    No Known Activations