© 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. 65127
    Prev
    Next
    INDEX
    Explanations

    yoga, training, traditions

    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
     Dart
    -0.07
    طاÙĤ
    -0.07
    ä¸īé¤IJ
    -0.07
    åĩºå±Ģ
    -0.07
    outh
    -0.06
     phenotype
    -0.06
    éĿł
    -0.06
    åĪ»éª¨
    -0.06
    纹
    -0.06
     cerem
    -0.06
    POSITIVE LOGITS
    çĴ
    0.09
    æĪIJä½Ľ
    0.08
    è§Ĥ
    0.08
    èĪ¬èĭ¥
    0.08
    æ¸ħåĩĢ
    0.08
    åįģæĸ¹
    0.08
    æĹłä¸Ĭ
    0.07
    ä½Ľæ³ķ
    0.07
    æİĪ
    0.07
    åĬłæĮģ
    0.07
    Activations Density 0.002%

    No Known Activations