© 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. 61598
    Prev
    Next
    INDEX
    Explanations

    victims and crime

    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
    身æķħ
    -0.07
    leman
    -0.07
    ascal
    -0.07
     tâ
    -0.07
    汶
    -0.07
    ché
    -0.07
    RelativeTo
    -0.07
    è·¯ä¸ľ
    -0.07
    _APPLICATION
    -0.07
     extraordinaire
    -0.07
    POSITIVE LOGITS
     unsus
    0.15
     unprotected
    0.14
    æĹłè¾ľ
    0.12
    åıĹ害
    0.10
    被害
    0.10
     unwitting
    0.10
    èĢĮ代ä¹ĭ
    0.09
     vulnerable
    0.09
    被ä»ĸ
    0.09
    ä¿ĿæĬ¤çļĦ
    0.09
    Activations Density 0.556%

    No Known Activations