© 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. 34476
    Prev
    Next
    INDEX
    Explanations

    established that legal violations

    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
    eka
    -0.07
    éĢĴ交ä¸Ĭè¯īçĬ¶
    -0.07
    åı«åģļ
    -0.07
    羣åģĩ
    -0.07
    车éĻ©
    -0.07
    ä¸ĸçķĮåIJĦåľ°çļĦ
    -0.07
    æŁIJ
    -0.06
    çĸijä¼¼è¿Ŀè§Ħ
    -0.06
    å¼ĢåºŃåħ¬åijĬ
    -0.06
    æľīæŶåĢĻ
    -0.06
    POSITIVE LOGITS
    ä½ķåĨµ
    0.09
     nexus
    0.09
    åĨµä¸Ķ
    0.09
    æĽ´ä½ķåĨµ
    0.09
    å®ŀè´¨æĢ§
    0.08
     unlaw
    0.08
     Huff
    0.08
    å·²è¶ħè¿ĩ
    0.08
    è¯ģæį®è¯ģæĺİ
    0.08
    ottle
    0.08
    Activations Density 0.060%

    No Known Activations