© 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. 34727
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ëĿ¼ëıĦ
    -0.08
    æĭĽèĤ¡
    -0.08
    ibern
    -0.08
    ä¸īåħ¬
    -0.08
    徨
    -0.08
     Lượt
    -0.07
    angkat
    -0.07
    -front
    -0.07
    åĢ¼åıĭ
    -0.07
    atalog
    -0.07
    POSITIVE LOGITS
    ä¸Ģéģį
    0.07
     pretty
    0.07
    ligh
    0.06
    åIJijãģį
    0.06
    kov
    0.06
    æŃĩ
    0.06
    exit
    0.06
    æĮº
    0.06
    å¿ĥçĶŁ
    0.06
    åı¯çĶ¨äºİ
    0.06
    Activations Density 0.075%

    No Known Activations