© 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. 58911
    Prev
    Next
    INDEX
    Explanations

    concentration camp

    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
    çois
    -0.09
    帮åĬ©ä¸Ńå¿ĥ
    -0.09
    åĭĩå¾Ģ缴åīį
    -0.09
    erais
    -0.08
    abase
    -0.08
    ctors
    -0.08
    åħ¨å¿ĥåħ¨æĦı
    -0.08
    áĥłáĥĿ
    -0.08
    æĶ¾é¡Į
    -0.08
    egers
    -0.08
    POSITIVE LOGITS
    è¯į
    0.06
    çĥŃ
    0.06
    (?)
    0.06
    HC
    0.06
     man
    0.06
     reb
    0.06
    æ³
    0.06
    Âł
    0.06
    -
    0.06
    æ¼Ĥ
    0.05
    Activations Density 0.181%

    No Known Activations