© 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. 19964
    Prev
    Next
    INDEX
    Explanations

    1, Australia

    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
    åĴĮåĪ©çĶ¨
    -0.08
     round
    -0.07
    bre
    -0.07
    round
    -0.06
    поÑĢа
    -0.06
    rix
    -0.06
    skom
    -0.06
    iro
    -0.06
    ëĿ¼ë©´
    -0.06
    kom
    -0.06
    POSITIVE LOGITS
    Kelu
    0.08
    .libs
    0.07
    åľ°ä¹ħ
    0.07
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.07
     Teixe
    0.07
     dégrad
    0.07
    èĬ±æľ¨
    0.07
    ä¼ģä¸ļä¿¡æģ¯
    0.07
    akte
    0.07
    Funk
    0.07
    Activations Density 0.034%

    No Known Activations