© 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. 34737
    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
    éĨĴ
    -0.07
    IVO
    -0.07
    ³
    -0.06
    åĪ°æѤ
    -0.06
    浩çĦ¶
    -0.06
     pragmatic
    -0.06
    ↵↵
    -0.05
    ↵↵↵
    -0.05
    模ç³Ĭ
    -0.05
    bart
    -0.05
    POSITIVE LOGITS
    ï¸ı
    0.09
    tene
    0.08
    ê´´
    0.08
    nton
    0.08
    olist
    0.08
    stown
    0.08
    inei
    0.08
    tif
    0.08
    fäh
    0.08
    éĩij森
    0.08
    Activations Density 0.000%

    No Known Activations