© 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. 20259
    Prev
    Next
    INDEX
    Explanations

    new, reduction, chronic, acute, infinite

    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
    ën
    -0.07
    issen
    -0.07
     Doub
    -0.07
     pó
    -0.07
     Dub
    -0.06
     ór
    -0.06
    éĩĮäºļ
    -0.06
    žno
    -0.06
    eltas
    -0.06
    neath
    -0.06
    POSITIVE LOGITS
    ecute
    0.07
    Į¨
    0.07
    ä¸Ń央社
    0.07
    è°ĥçłĶåijĺ
    0.07
    ä¸įä¹°
    0.07
    оÑĤов
    0.06
    oco
    0.06
     totiž
    0.06
    ][_
    0.06
    acific
    0.06
    Activations Density 0.126%

    No Known Activations