© 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. 15656
    Prev
    Next
    INDEX
    Explanations

    appointed a, SingleFileGenerator, Osama bin, administrative center, pilot or

    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¸į欲
    -0.08
    Įĵ
    -0.08
    arms
    -0.08
    çĸı
    -0.07
    è¯Ĺæĥħ
    -0.07
    ç»Ļæľĭåıĭ
    -0.07
    биÑĢ
    -0.07
    anken
    -0.07
    ØŃÙĬÙĨ
    -0.07
    weite
    -0.07
    POSITIVE LOGITS
    åŁºçĤ¹
    0.10
    åľ¨åħ¶ä¸Ń
    0.09
    æľĢé«ĺçĤ¹
    0.09
     point
    0.09
    ç»ĵçĤ¹
    0.09
     focal
    0.09
     titik
    0.09
    åĿIJéķĩ
    0.09
     ÑĨенÑĤÑĢ
    0.09
    ศูà¸Ļยà¹Įà¸ģลาà¸ĩ
    0.08
    Activations Density 0.809%

    No Known Activations