© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2293
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    çļĦåħīèį£
    -0.06
     esib
    -0.06
    çķĮ线
    -0.06
    ä¹ĭå®Ŀ
    -0.06
    dling
    -0.06
    inja
    -0.06
     limites
    -0.06
    geld
    -0.06
    ä¸įæ³ķåĪĨåŃIJ
    -0.06
    od
    -0.06
    POSITIVE LOGITS
    Winvalid
    0.07
    kest
    0.07
    ://${
    0.07
    ãĥ¶
    0.07
    BitFields
    0.07
    å¾·éĩĮ
    0.07
    éĩijå±±
    0.07
    ække
    0.07
    warf
    0.07
    utas
    0.07
    Activations Density 0.003%

    No Known Activations