© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2651
    Prev
    Next
    INDEX
    Explanations

    Prior Art

    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
    çļĦéģĵ
    -0.08
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    ick
    -0.07
    icking
    -0.07
    åıªæľīèĩªå·±
    -0.07
     pseud
    -0.07
    uhl
    -0.07
    arken
    -0.07
     others
    -0.07
    åģļ人
    -0.07
    POSITIVE LOGITS
    ä¸ĩæĪ·
    0.07
    utat
    0.06
    _-_
    0.06
    WithContext
    0.06
    èĦĬ
    0.06
    RIA
    0.06
    -with
    0.06
    ä¸ŃåİŁ
    0.06
     ìŀħ
    0.06
    èĽ
    0.06
    Activations Density 0.010%

    No Known Activations