© 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. 48322
    Prev
    Next
    INDEX
    Explanations

    but followed by contrast

    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
    èĢĮæľª
    -0.07
    ä¸įåĨįæĺ¯
    -0.07
    绾
    -0.07
     exploited
    -0.07
    ä¸įä¿¡
    -0.07
    å°±ä¸įæĺ¯
    -0.07
     hag
    -0.06
    ëł¹
    -0.06
    ç¥ŀå±±
    -0.06
    æĹłæĥħ
    -0.06
    POSITIVE LOGITS
    ếm
    0.08
    ungan
    0.07
    èĢĥçļĦ
    0.07
    adir
    0.07
    èĦļæŃ¥
    0.07
    èģŀ
    0.07
    æŃ·
    0.07
    éºĴ
    0.07
    .Addr
    0.07
     logically
    0.07
    Activations Density 0.020%

    No Known Activations