© 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. 41428
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    åı¯æĥ³
    -0.10
     @}
    -0.09
    	↵↵↵
    -0.09
    æŃ¤èµ·
    -0.09
    imaan
    -0.08
    ä¹ĭä¸Ģå°±æĺ¯
    -0.08
     inilah
    -0.08
     successivo
    -0.08
    ãģĹãģıãģ¯
    -0.08
     conséquent
    -0.08
    POSITIVE LOGITS
    Âł
    0.07
    ³³³³³³³³
    0.07
    	B
    0.07
    B
    0.06
    ãĢĢ
    0.06
    ³³³³
    0.06
    ³³
    0.06
    âĢ
    0.06
     B
    0.06
    äºĮæĺ¯
    0.06
    Activations Density 0.042%

    No Known Activations