© 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. 44547
    Prev
    Next
    INDEX
    Explanations

    inhibition and stabilization

    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
    æ¿Ģæĥħ
    -0.07
    ÙĨÙĬÙĨ
    -0.07
    emberg
    -0.07
     Freed
    -0.07
    ÐĿÐļ
    -0.06
    æĺ¯ä¸ĢåĪĩ
    -0.06
    лÑĥм
    -0.06
     опÑĢедел
    -0.06
    æķ²
    -0.06
    дев
    -0.06
    POSITIVE LOGITS
    ä»İèĢĮè¾¾åĪ°
    0.10
     disrupt
    0.08
    ören
    0.08
     neutral
    0.08
     пÑĥÑĤем
    0.08
     Renders
    0.07
     temporarily
    0.07
     Halt
    0.07
    éĺ»æŃ¢
    0.07
     disrupting
    0.07
    Activations Density 0.137%

    No Known Activations