© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46711
    Prev
    Next
    INDEX
    Explanations

    robbery and theft

    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
    äºİäºĭ
    -0.08
    èĦļä¸ĭ
    -0.07
     заÑıвкÑĥ
    -0.07
    spf
    -0.07
    éħª
    -0.07
    wane
    -0.07
    åĮĸåIJĪ
    -0.06
     impass
    -0.06
    scheduler
    -0.06
    Kosten
    -0.06
    POSITIVE LOGITS
    çĽĹçªĥ
    0.11
    åĽ¢ä¼Ļ
    0.10
    çĽĹ
    0.10
    å¾Ĺæīĭ
    0.09
     stealing
    0.09
     cắp
    0.09
     loot
    0.09
    bery
    0.09
    æĬ¢åĬ«
    0.09
    ä¸Ģ空
    0.09
    Activations Density 0.041%

    No Known Activations