© 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. 3380
    Prev
    Next
    INDEX
    Explanations

    algebraically closed fields and modules

    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
    ÙĪع
    -0.07
    atan
    -0.07
    dling
    -0.06
    اسب
    -0.06
    åĬ¨çī©çļĦ
    -0.06
    action
    -0.06
    ë°ĸìĹIJ
    -0.06
    omen
    -0.06
     discr
    -0.06
    çĶ¨åĪ°çļĦ
    -0.06
    POSITIVE LOGITS
    pawn
    0.07
    æ¶ĤæĸĻ
    0.07
    _PW
    0.07
    åľ°å¹³
    0.07
    æĺĵçĪĨ
    0.07
    igator
    0.07
    åij¨æĺŁ
    0.07
    ervi
    0.07
    ãĥķãĥªãĥ¼
    0.07
    ände
    0.06
    Activations Density 0.002%

    No Known Activations