© 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. 21219
    Prev
    Next
    INDEX
    Explanations

    after starting words like "I", "She", "checked"

    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
    جÙĬر
    -0.09
     @}
    -0.08
    cul
    -0.08
    足çļĦ
    -0.08
    aranya
    -0.07
    antium
    -0.07
    åIJİçĶ¨
    -0.07
    ä½łåį´
    -0.07
    ç¼¥
    -0.07
    £
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪè¦ģ
    0.07
     myself
    0.07
    é¦ĸåħĪéľĢè¦ģ
    0.07
    ä»Ķç»Ĩ
    0.06
     gathering
    0.06
    é¦ĸåħĪ
    0.06
    LOS
    0.06
    irst
    0.06
    les
    0.06
     carefully
    0.06
    Activations Density 0.002%

    No Known Activations