© 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. 11642
    Prev
    Next
    INDEX
    Explanations

    projected view

    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
    sker
    -0.09
    åģ¿
    -0.08
    hä
    -0.08
    æīĵè¿Ľ
    -0.08
    éĵ¿
    -0.08
     ÑĤипо
    -0.07
    æĥ¹
    -0.07
    stant
    -0.07
    çĶ¨èµ·æĿ¥
    -0.07
    ongs
    -0.07
    POSITIVE LOGITS
    Ã¼ÅŁ
    0.07
     view
    0.07
    èĥ½çľĭåĪ°
    0.07
     glimps
    0.07
    çľĭåĪ°çļĦæĺ¯
    0.07
    å¨ĺå¨ĺ
    0.07
    å²±
    0.06
    çľĭåĪ°çļĦ
    0.06
    æįķæįī
    0.06
    æķĪæŀľåĽ¾
    0.06
    Activations Density 0.001%

    No Known Activations