© 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. 25322
    Prev
    Next
    INDEX
    Explanations

    `.hashCode` `AttachDbFilename` `vent length`

    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
    _BOTH
    -0.09
    ä¸į论æĺ¯
    -0.09
    çĦ¡è«ĸæĺ¯
    -0.09
    [['
    -0.08
     zowel
    -0.08
    æĹłè®ºæĺ¯
    -0.08
    ë¹Ļ
    -0.08
     zarówno
    -0.08
    å¼ıåĴĮ
    -0.08
    ä¸į管æĺ¯
    -0.08
    POSITIVE LOGITS
    å°ıå¿ĥ
    0.06
    rene
    0.06
    æľ¨åģ¶
    0.06
    éģŃ
    0.06
     أث
    0.05
    0.05
    å±İ
    0.05
    åĪ«
    0.05
    çĴŀ
    0.05
    æħİ
    0.05
    Activations Density 0.553%

    No Known Activations