© 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. 19794
    Prev
    Next
    INDEX
    Explanations

    mathematical variable r

    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
    áĥ£áĥłáĥĺ
    -0.17
    ek
    -0.12
    áĥ£áĥł
    -0.10
    en
    -0.10
    raries
    -0.10
    áĥĿáĥij
    -0.09
    à¸ģà¹Į
    -0.09
    à¸Ļà¹Į
    -0.09
    ×Ļ×Ļ×Ŀ
    -0.09
    em
    -0.08
    POSITIVE LOGITS
    ণ
    0.11
    abbit
    0.10
    untime
    0.10
    iginal
    0.10
    ignano
    0.09
    ण
    0.09
    outines
    0.09
    Åijl
    0.09
    asmus
    0.09
    णा
    0.09
    Activations Density 0.041%

    No Known Activations