© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62728
    Prev
    Next
    INDEX
    Explanations

    unless otherwise

    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
    ç²¾å¿ĥ
    -0.07
    人åķĬ
    -0.07
    æľ¬åŃ£
    -0.07
    anford
    -0.07
    ç«ĭåį³ä¸ĭè½½
    -0.07
    mart
    -0.07
    人å¿ĥ
    -0.07
    hini
    -0.06
    amna
    -0.06
    éĤı
    -0.06
    POSITIVE LOGITS
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.11
     expressly
    0.09
    è§Ħå®ļçļĦ
    0.08
    åĴĮåĽ½å®¶
    0.08
    æŁIJäºĽ
    0.08
    åı¦æľī
    0.07
    åĽ½å®¶æľºåħ³
    0.07
    åĪĹ举
    0.07
     otherwise
    0.07
     specifically
    0.07
    Activations Density 0.043%

    No Known Activations