© 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. 44840
    Prev
    Next
    INDEX
    Explanations

    subcutaneous tissue

    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
    é¢ij
    -0.08
     ÑĩÑĥг
    -0.08
    å·¡
    -0.07
    西äºŀ
    -0.07
    (bucket
    -0.07
    antik
    -0.07
    个人页
    -0.07
     Tand
    -0.07
    apun
    -0.07
    quat
    -0.07
    POSITIVE LOGITS
    å±ĤçļĦ
    0.11
     layer
    0.11
    å±Ĥ
    0.10
     layers
    0.10
    æ·±å±Ĥ
    0.10
    æ·±å¤Ħ
    0.10
    層
    0.10
    å±Ĥ次
    0.10
     vascular
    0.09
     surrounding
    0.09
    Activations Density 0.254%

    No Known Activations