© 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. 58806
    Prev
    Next
    INDEX
    Explanations

    macular degeneration

    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
    æķŀå¼Ģ
    -0.07
    åħ¶è¡Į为
    -0.07
    强身
    -0.07
     antic
    -0.07
    çķĻé¦Ļ
    -0.07
    å·¥åķĨ
    -0.07
    åIJģ
    -0.07
     eco
    -0.06
    badge
    -0.06
     Iron
    -0.06
    POSITIVE LOGITS
    è§Ĩç½ijèĨľ
    0.14
     retina
    0.14
    è§ĨåĬĽ
    0.14
    失æĺİ
    0.13
    æĦŁåħī
    0.13
     optical
    0.12
     optic
    0.12
     Optical
    0.12
     blindness
    0.12
    对è§Ĩ
    0.12
    Activations Density 0.295%

    No Known Activations