© 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. 7160
    Prev
    Next
    INDEX
    Explanations

    guards refused, right free

    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
    çĥŃéŨæĸĩç«ł
    -0.09
    VERN
    -0.08
    BorderColor
    -0.08
    %C
    -0.08
    èĺĭ
    -0.08
     ç§ģ
    -0.08
    ulu
    -0.08
    acker
    -0.08
    OptionsMenu
    -0.08
    群æĺŁ
    -0.07
    POSITIVE LOGITS
    0.10
    y
    0.06
     ë°ĺ
    0.06
     \%
    0.06
    't
    0.06
     \
    0.06
    åľ¨åIJĮä¸Ģ
    0.06
     '
    0.06
    ']]
    0.06
     mar
    0.06
    Activations Density 0.008%

    No Known Activations