© 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. 49050
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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
    éļ¶å±ŀ
    -0.07
     nexus
    -0.06
    Desk
    -0.06
    season
    -0.06
    ram
    -0.06
    esten
    -0.06
    çĮ®
    -0.06
    ÙĥÙĬÙĨ
    -0.06
    åĵ¨
    -0.06
    æºľ
    -0.06
    POSITIVE LOGITS
    çļĦä¸ĢåįĬ
    0.09
    éĻ¤ä»¥
    0.08
    SqlCommand
    0.07
    æ¥ļ天
    0.07
    пок
    0.07
     Martial
    0.07
    踪
    0.07
    åij¼æ°Ķ
    0.07
    szak
    0.07
    åı±
    0.07
    Activations Density 0.108%

    No Known Activations