© 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. 58972
    Prev
    Next
    INDEX
    Explanations

    not, unrelated, outside

    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
     Ruf
    -0.07
    gary
    -0.07
     Hammer
    -0.07
    ÑģÑĤок
    -0.07
    æľīä»Ģä¹ĪéĹ®é¢ĺ
    -0.07
    缺çĤ¹æĺ¯
    -0.07
     Flake
    -0.07
    orr
    -0.07
    gid
    -0.07
    åĩıå°ij对
    -0.07
    POSITIVE LOGITS
    åİŁå®ļ
    0.09
     intended
    0.09
     unintended
    0.07
     unrelated
    0.07
    eyond
    0.07
    åİŁæľ¬
    0.07
    ä¸įåIJĪçIJĨ
    0.07
    ä¸įçIJĨ
    0.07
    oplevel
    0.07
    åİŁçĶŁ
    0.07
    Activations Density 0.187%

    No Known Activations