© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34916
    Prev
    Next
    INDEX
    Explanations

    typing and .List

    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
    Negative Logits
    ÚĨÙĩ
    -0.07
    ä¼Ļé£Ł
    -0.07
    äºĽä»Ģä¹Ī
    -0.07
    ertes
    -0.07
    çīĪ主
    -0.07
    iba
    -0.06
    çıį
    -0.06
    —an
    -0.06
    leta
    -0.06
    åŀ®
    -0.06
    POSITIVE LOGITS
     Sanc
    0.08
    []"
    0.08
    vou
    0.07
     overrun
    0.07
    inding
    0.07
    ×ķ×Ĵ
    0.07
    ogramm
    0.07
    å·´å¡ŀ
    0.07
    yna
    0.06
    ÙĨÙĬÙĩ
    0.06
    Activations Density 0.001%

    No Known Activations