© 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. 60871
    Prev
    Next
    INDEX
    Explanations

    special characters and code snippets

    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
    Reality
    -0.08
    ius
    -0.07
    ¸
    -0.07
     trou
    -0.07
    µ
    -0.07
    ijas
    -0.07
     Dmit
    -0.07
     kümm
    -0.06
    AndGet
    -0.06
    ToDevice
    -0.06
    POSITIVE LOGITS
    çĶļèĩ³æľī
    0.07
    γά
    0.07
    缮çŀª
    0.07
    ourn
    0.07
    оÑĩи
    0.06
    éĤ£ä¹ĪæĪij们
    0.06
    åıįéĿ¢
    0.06
    设æ³ķ
    0.06
    è®¤çľŁçłĶ究
    0.06
    æľīç¥ŀ
    0.06
    Activations Density 0.055%

    No Known Activations