© 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. 38940
    Prev
    Next
    INDEX
    Explanations

    to use / can make

    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
    _Debug
    -0.07
    ssen
    -0.07
    为äºĨæĽ´å¥½åľ°
    -0.07
    为确ä¿Ŀ
    -0.07
    为äºĨæĽ´å¥½çļĦ
    -0.07
    richter
    -0.07
    é«ĺå¾·
    -0.06
    ç¡®ä¿Ŀå®īåħ¨
    -0.06
    ocused
    -0.06
     coll
    -0.06
    POSITIVE LOGITS
    æĹłéľĢ
    0.11
    åħį
    0.11
    åħįåİ»
    0.10
    ä¸įéľĢè¦ģ
    0.10
    便æį·
    0.10
    çĦ¡éľĢ
    0.09
    åĽ½äº§åĮĸ
    0.09
    æijĨèĦ±
    0.09
     independence
    0.09
    åĩıå°ij对
    0.09
    Activations Density 0.653%

    No Known Activations