© 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. 37653
    Prev
    Next
    INDEX
    Explanations

    high regard and value

    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
    Negative Logits
    oucher
    -0.08
    æīĢ欲è¨Ģ
    -0.07
    lude
    -0.07
    combe
    -0.07
    ÑĩаÑĤ
    -0.07
    éĢŀ
    -0.07
    äsch
    -0.06
    angsa
    -0.06
    ä¸Ģè¶Ł
    -0.06
     khiếu
    -0.06
    POSITIVE LOGITS
    æľīåĬł
    0.13
    éĩįè§Ĩ
    0.10
     importance
    0.10
     value
    0.09
    æݨå´ĩ
    0.09
    对å¾ħ
    0.09
    -worthy
    0.09
    çļĦéĩįè§Ĩ
    0.09
    追æį§
    0.09
    åľ°ä½į
    0.09
    Activations Density 0.147%

    No Known Activations