© 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. 46982
    Prev
    Next
    INDEX
    Explanations

    sort by, ranking

    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
    ook
    -0.08
     Eaton
    -0.07
    èİİ
    -0.07
    ãģĦãģª
    -0.07
    iola
    -0.07
    å»
    -0.07
    éĹ®åıĬ
    -0.07
    ardt
    -0.07
    åıĸèĩª
    -0.07
     Nav
    -0.07
    POSITIVE LOGITS
    æİĴåºı
    0.14
    è¿Ľè¡Įæ¯Ķè¾ĥ
    0.13
    æ¯Ķè¾ĥ
    0.13
     comparative
    0.13
     compare
    0.12
     ranking
    0.12
     comparing
    0.12
    èĢħä¼ĺåħĪ
    0.12
     comparison
    0.11
    çļĦæ¯Ķè¾ĥ
    0.11
    Activations Density 0.111%

    No Known Activations