© 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. 44050
    Prev
    Next
    INDEX
    Explanations

    quotes and names after punctuation

    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
    úm
    -0.08
    éĨį
    -0.07
    feh
    -0.07
    çļĦæįŁå¤±
    -0.07
     Bergamo
    -0.07
    æ´ĭ
    -0.07
    ائÙĨ
    -0.07
    elv
    -0.06
    Ùĥار
    -0.06
    æ¶Ľ
    -0.06
    POSITIVE LOGITS
    èĤĨ
    0.07
    æľĢåIJİä¸Ģ天
    0.07
    oba
    0.06
    ä¹ĿæĪIJ
    0.06
    inel
    0.06
     reasoning
    0.06
    zeg
    0.06
    zs
    0.06
    ehold
    0.06
    ACLE
    0.06
    Activations Density 0.735%

    No Known Activations