© 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. 8350
    Prev
    Next
    INDEX
    Explanations

    math subjects and problems

    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
    ities
    -0.10
    ListOf
    -0.08
    人æ°ijåĮ»éĻ¢
    -0.08
    lename
    -0.08
    theless
    -0.08
    ÑħваÑĤи
    -0.08
    inde
    -0.07
    سازÛĮ
    -0.07
    ategy
    -0.07
    ICODE
    -0.07
    POSITIVE LOGITS
    ed
    0.11
    aan
    0.11
    aç
    0.10
    en
    0.09
    aic
    0.09
    åĦ¿
    0.09
    ers
    0.09
    eson
    0.09
    nasium
    0.09
    åĦ¿çļĦ
    0.09
    Activations Density 0.020%

    No Known Activations