© 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. 56365
    Prev
    Next
    INDEX
    Explanations

    equation, function, series

    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
     ÐĶополни
    -0.08
    ç§ijç§ijéķ¿
    -0.08
    ستاÙĨ
    -0.07
    iselect
    -0.07
    bsd
    -0.07
    ÙĪاÙĨÙĬ
    -0.07
     оÑĤÑĢÑĭ
    -0.07
    æĨĶ
    -0.07
    urement
    -0.07
    PlainText
    -0.07
    POSITIVE LOGITS
    ég
    0.06
    omot
    0.06
    meister
    0.06
    顾åıĬ
    0.06
    elter
    0.06
    ä¸ĭ线
    0.06
    rica
    0.06
    ä¹±
    0.06
     Jonas
    0.06
    çĽ¯
    0.06
    Activations Density 0.032%

    No Known Activations