© 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. 22324
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

    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
    althy
    -0.07
    ep
    -0.07
     непеÑĢе
    -0.06
     ep
    -0.06
     indexed
    -0.06
     kas
    -0.06
    .ir
    -0.06
    æĴ
    -0.06
    alcon
    -0.06
    ARING
    -0.06
    POSITIVE LOGITS
    ipper
    0.08
    emens
    0.08
    clin
    0.08
    anja
    0.08
    anj
    0.08
    anca
    0.07
    (expect
    0.07
    schau
    0.07
    ÙĬاء
    0.07
    èIJĿ
    0.07
    Activations Density 0.009%

    No Known Activations