© 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. 37668
    Prev
    Next
    INDEX
    Explanations

    wingspan

    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
    ä¸įéĢļ
    -0.07
    çĵ¶è£ħ
    -0.07
    éĺ±
    -0.07
    åĪ°çļĦ
    -0.07
    管çIJĨå±Ģ
    -0.06
    æĢ»å±Ģ
    -0.06
    åĩ¿
    -0.06
    å±Ģ
    -0.06
    åĩºå±Ģ
    -0.06
    éĢļçļĦ
    -0.06
    POSITIVE LOGITS
    宽大
    0.10
     wings
    0.10
    -wing
    0.10
    ç¿ħèĨĢ
    0.10
    ç¿ħ
    0.09
     blades
    0.09
    éĿ¢ç©į
    0.09
    -shaped
    0.09
    éĿ¢ç§¯
    0.09
    çīĩçļĦ
    0.09
    Activations Density 0.071%

    No Known Activations