© 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. 51799
    Prev
    Next
    INDEX
    Explanations

    segment

    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
    enticated
    -0.10
    teen
    -0.08
    ÅĽmy
    -0.08
    IMUM
    -0.08
    à¸Ĺà¹Į
    -0.08
    lander
    -0.08
    essant
    -0.08
    ä¹ĭå¢ĥ
    -0.08
    shire
    -0.08
    ksen
    -0.08
    POSITIVE LOGITS
     بÙĨدÛĮ
    0.09
    wise
    0.09
    antically
    0.09
    edly
    0.08
    تع
    0.08
    ry
    0.08
    راÙĨ
    0.08
    س
    0.08
    à¥įस
    0.08
    ë³Ħ
    0.08
    Activations Density 0.012%

    No Known Activations