© 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. 4345
    Prev
    Next
    INDEX
    Explanations

    specialized adaptations

    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
    鼶
    -0.08
    é¡»çŁ¥
    -0.08
    èįĴ
    -0.07
    æľŁéĻIJ
    -0.07
     mixed
    -0.07
    鼶æĺŁ
    -0.07
    uhan
    -0.07
    еÑĩи
    -0.07
    insk
    -0.06
     either
    -0.06
    POSITIVE LOGITS
     adaptations
    0.12
     specialized
    0.09
    以éĢĤåºĶ
    0.09
    åıijè¾¾
    0.08
     specialised
    0.08
     пÑĢиÑģпоÑģоб
    0.08
    {{{
    0.08
    éĥ½æĺ¯ä¸ºäºĨ
    0.08
    å°±æĺ¯ä¸ºäºĨ
    0.08
    ä¹Łæĺ¯ä¸ºäºĨ
    0.08
    Activations Density 0.034%

    No Known Activations