© 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. 12373
    Prev
    Next
    INDEX
    Explanations

    for, in

    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
    reit
    -0.07
    ruk
    -0.07
    weisen
    -0.06
    代çłģå¦Ĥä¸ĭ
    -0.06
     أجÙĦ
    -0.06
    lige
    -0.06
    ogg
    -0.06
    .utf
    -0.06
    为æ°ij
    -0.06
    ligen
    -0.06
    POSITIVE LOGITS
    orem
    0.09
     entanto
    0.09
    ,is
    0.08
    ,the
    0.08
    ,to
    0.08
    ,it
    0.08
    åį³å°ĨåĪ°æĿ¥çļĦ
    0.07
     _______,
    0.07
    structors
    0.07
    -',
    0.07
    Activations Density 0.076%

    No Known Activations