© 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. 45638
    Prev
    Next
    INDEX
    Explanations

    quotes followed by names or authors

    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
    ç³»
    -0.06
    ied
    -0.06
     пÑĢинÑĨипи
    -0.06
     familiar
    -0.06
     اÙĦØŃÙħد
    -0.06
    çıĪ
    -0.06
     rout
    -0.06
    äºĨåı£æ°Ķ
    -0.06
    [:,:
    -0.06
    交åıī
    -0.06
    POSITIVE LOGITS
    对人
    0.08
    itora
    0.08
    лай
    0.08
    èѦåı¥
    0.07
    è½¼
    0.07
    cré
    0.07
    åIJį人
    0.07
    vore
    0.07
    æł¼è¨Ģ
    0.07
    insta
    0.07
    Activations Density 0.105%

    No Known Activations