© 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. 33246
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    otre
    -0.07
    çŀ
    -0.07
    æ¼Ĥ
    -0.07
    oley
    -0.07
    ä¸ĢæľŁ
    -0.06
    ×Ļת×Ķ
    -0.06
    Ø·ÙĨ
    -0.06
     virt
    -0.06
    çĶ¸
    -0.06
    .utf
    -0.06
    POSITIVE LOGITS
    cez
    0.07
    æĹ
    0.07
    enho
    0.07
     Meld
    0.07
    azzi
    0.07
    amar
    0.06
    té
    0.06
     specifie
    0.06
    esia
    0.06
    æľīä¸Ģ款
    0.06
    Activations Density 0.024%

    No Known Activations