© 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. 28283
    Prev
    Next
    INDEX
    Explanations

    URL path separators

    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
    lerc
    -0.08
    elib
    -0.07
    engo
    -0.07
    adari
    -0.07
    opr
    -0.07
    [$
    -0.07
    [user
    -0.06
    æľ¬åľº
    -0.06
    :date
    -0.06
    apa
    -0.06
    POSITIVE LOGITS
    ีà¸ļ
    0.08
     sekaligus
    0.08
    olley
    0.07
    ีม
    0.07
    çļĦåIJ§
    0.07
    ë°ı
    0.07
     {:?}",
    0.07
    ائÙĬ
    0.07
    anser
    0.07
    alone
    0.06
    Activations Density 0.180%

    No Known Activations