© 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. 43088
    Prev
    Next
    INDEX
    Explanations

    latex control sequences

    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
    urf
    -0.09
    err
    -0.08
    -d
    -0.07
    urer
    -0.06
    ee
    -0.06
    uck
    -0.06
    ÑĮÑİ
    -0.06
    elm
    -0.06
    -
    -0.06
    ±
    -0.06
    POSITIVE LOGITS
    اش
    0.09
    à¹Į
    0.08
    witz
    0.08
    aires
    0.08
    åļĵ
    0.08
    ании
    0.07
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    anyol
    0.07
    cito
    0.07
    !--
    0.07
    Activations Density 0.035%

    No Known Activations