© 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. 44205
    Prev
    Next
    INDEX
    Explanations

    special characters or quotes

    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
     Werb
    -0.06
    ukan
    -0.06
    ×ķ×ķ
    -0.06
    .additional
    -0.06
    -0.06
     Pioneer
    -0.05
    çĿ¡è¢ĭ
    -0.05
    /data
    -0.05
    |
    -0.05
    ell
    -0.05
    POSITIVE LOGITS
     mixed
    0.11
     Mixed
    0.10
    mixed
    0.10
    Mixed
    0.10
    æ··åIJĪ
    0.09
    Ùİاب
    0.08
    夫çļĦ
    0.08
    好çļĦ产åĵģ
    0.08
    æ··
    0.08
     подлежа
    0.08
    Activations Density 0.331%

    No Known Activations