© 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. 54942
    Prev
    Next
    INDEX
    Explanations

    spoiled, True, killed, 0, if

    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
    æĥļ
    -0.08
    heu
    -0.08
    .adjust
    -0.08
    lieg
    -0.07
    ç§ĭæľĪ
    -0.07
    arit
    -0.07
     évolu
    -0.07
    izzo
    -0.07
    heim
    -0.07
    engeb
    -0.07
    POSITIVE LOGITS
    æķ´ä½ĵçļĦ
    0.11
    æķ´ä½ĵ
    0.10
    æķ´ä¸ª
    0.09
    çļĦæķ´ä½ĵ
    0.09
     overall
    0.09
     tainted
    0.09
    æķ´é«Ķ
    0.08
    åħ¨çĽĺ
    0.08
    ä¸Ģ票
    0.08
    ä½Ĩåıªè¦ģ
    0.08
    Activations Density 0.045%

    No Known Activations