© 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. 11441
    Prev
    Next
    INDEX
    Explanations

    sqrt and mathematical notations

    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
    ä¸ºçĽ®æłĩ
    -0.08
    รà¸ĩà¹ģ
    -0.08
    çĤ¹å°ı
    -0.08
    æĢ»åľ¨
    -0.08
     Séné
    -0.08
    inkl
    -0.08
    度é«ĺ
    -0.08
    anh
    -0.08
    ç©«
    -0.08
    izzi
    -0.08
    POSITIVE LOGITS
    Concrete
    0.06
    éĥ½èĥ½å¤Ł
    0.06
    æIJĶ
    0.06
     hypo
    0.05
     $
    0.05
    _Con
    0.05
    stinian
    0.05
    ä½ıå®ħå°ıåĮº
    0.05
    Hooks
    0.05
    Į
    0.05
    Activations Density 0.004%

    No Known Activations