© 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. 878
    Prev
    Next
    INDEX
    Explanations

    better or rather than

    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
    å¿ħé¡»çļĦ
    -0.08
     REQUIRED
    -0.08
    ussi
    -0.08
     gerne
    -0.08
    å¿ħé¡»åħ·å¤ĩ
    -0.08
    رÙĬد
    -0.08
    æĺłåħ¥
    -0.07
    ä»ħæĺ¯
    -0.07
    å¾Īéĩįè¦ģçļĦ
    -0.07
    úk
    -0.07
    POSITIVE LOGITS
     than
    0.10
     inkább
    0.09
     kuin
    0.08
     sooner
    0.08
     rather
    0.08
     avoid
    0.08
     instead
    0.08
    å®ľ
    0.08
    åħįå¾Ĺ
    0.08
     daripada
    0.08
    Activations Density 0.109%

    No Known Activations