© 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. 20036
    Prev
    Next
    INDEX
    Explanations

    Once something is done/obtained/installed

    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
    endoza
    -0.07
    çļĦçī¹çĤ¹æĺ¯
    -0.07
    çĿĢéĩį
    -0.07
     közben
    -0.06
     +
    -0.06
    åİļå¾·
    -0.06
    缴æݥ就
    -0.06
     justamente
    -0.06
    Ùģا
    -0.06
    èĩ³ä»Ĭ
    -0.06
    POSITIVE LOGITS
    å·®ä¸įå¤ļäºĨ
    0.12
     xong
    0.10
    éĢī好
    0.09
     successfully
    0.09
     selesai
    0.09
    ëIJĺë©´
    0.09
    èIJ½å®ŀ好
    0.09
    å®ĮæĪIJåIJİ
    0.08
    æľīäºĨ
    0.08
    确认åIJİ
    0.08
    Activations Density 0.161%

    No Known Activations