© 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. 52048
    Prev
    Next
    INDEX
    Explanations

    Nazi, war, Dominion, claims, lord

    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
    çijļ
    -0.08
    游åŃIJ
    -0.08
     unbiased
    -0.07
     odb
    -0.07
    åħ¬éģĵ
    -0.07
    åĬªåĬĽä¸ĭ
    -0.07
     impar
    -0.07
    pras
    -0.07
    Moved
    -0.07
    cline
    -0.07
    POSITIVE LOGITS
    åļ£å¼ł
    0.10
    éĺ´
    0.09
    çĭ°çĭŀ
    0.09
    çŃĸåĪĴ
    0.09
    å¾Ĺæīĭ
    0.09
     targeting
    0.09
    æģIJåIJĵ
    0.09
    çĭŀ
    0.08
     terror
    0.08
    åĩ¶
    0.08
    Activations Density 0.375%

    No Known Activations