© 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. 46841
    Prev
    Next
    INDEX
    Explanations

    mild or minor severity

    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
    ä¸įåħīæĺ¯
    -0.09
    immy
    -0.08
    inka
    -0.08
    imba
    -0.08
    agan
    -0.08
    ä¸įåıª
    -0.07
     unnatural
    -0.07
     Ùħخت
    -0.07
    áĢ¬áĢ¸
    -0.07
    ç¨Ģ缺
    -0.07
    POSITIVE LOGITS
    轻微
    0.11
    轻微çļĦ
    0.11
     harmless
    0.11
     mild
    0.10
    轻度
    0.10
     minor
    0.10
     ê°Ģë²¼
    0.10
    è¾ĥè½»
    0.10
    åı¯èĩªè¡Į
    0.10
    è¼ķ
    0.10
    Activations Density 0.233%

    No Known Activations