© 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. 47848
    Prev
    Next
    INDEX
    Explanations

    why they chose specific version

    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
     “
    -0.08
     "
    -0.06
    æľª
    -0.06
    éģĤ
    -0.06
     aff
    -0.06
    :
    -0.05
     full
    -0.05
    çļĦè¿ĺæľī
    -0.05
    èĤ¡
    -0.05
    以ä¸Ĭ
    -0.05
    POSITIVE LOGITS
     particular
    0.11
     tertentu
    0.10
     bepaalde
    0.10
    åĽŃè·¯
    0.10
    æŁIJåĢĭ
    0.09
    æŁIJæŁIJ
    0.09
    isel
    0.09
    ابÙĬ
    0.09
    æŁIJäºĽ
    0.09
    åIJĦ项活åĬ¨
    0.09
    Activations Density 0.028%

    No Known Activations