© 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. 57752
    Prev
    Next
    INDEX
    Explanations

    on one hand

    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
     sela
    -0.08
    /]
    -0.08
    edet
    -0.08
    icker
    -0.07
    ä¸įäºĪæĶ¯æĮģ
    -0.07
    put
    -0.07
    ä¸İåIJ¦
    -0.07
    åīįåĽŀ
    -0.07
    icat
    -0.07
    richter
    -0.07
    POSITIVE LOGITS
    èĢĮ以
    0.07
    ä¼¼
    0.07
    å¤Ł
    0.06
    年代
    0.06
    osso
    0.06
    åıĪ说
    0.06
    Äı
    0.06
    ä¸ĭ
    0.06
    æľĿ天
    0.06
    oser
    0.06
    Activations Density 0.317%

    No Known Activations