© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29411
    Prev
    Next
    INDEX
    Explanations

    Jewish and Israeli people and history

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Servlet
    -0.08
    ëł¹
    -0.08
     ucwords
    -0.08
    æ
    -0.08
    åĭĥ
    -0.07
    añ
    -0.07
    àºĩ
    -0.07
    laud
    -0.07
    åĨķ
    -0.07
    åįİåºľ
    -0.07
    POSITIVE LOGITS
    çĬ¹å¤ª
    0.20
    çĬ¹å¤ªäºº
    0.17
    以èī²åĪĹ
    0.17
     Jewish
    0.16
     Israeli
    0.15
     Israel
    0.15
    Israel
    0.14
    Israeli
    0.14
     Jews
    0.14
     ìĿ´ìĬ¤ëĿ¼ìĹĺ
    0.13
    Activations Density 0.434%

    No Known Activations