© 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. 34500
    Prev
    Next
    INDEX
    Explanations

    hypothetical or unusual scenarios

    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
    ersch
    -0.07
     usein
    -0.07
    æĢ»æĺ¯åľ¨
    -0.07
    engeb
    -0.07
     Dep
    -0.07
    regar
    -0.07
    ç¾ļ
    -0.07
    çİĭçīĮ
    -0.07
    å°ıèıľ
    -0.07
    .onStart
    -0.07
    POSITIVE LOGITS
    æŀģ端
    0.10
     unconventional
    0.09
    çIJĨ论ä¸Ĭ
    0.09
    å¥ĩçī¹çļĦ
    0.08
     theoretically
    0.08
     hypothetical
    0.08
     unusual
    0.08
     would
    0.08
    åĢĴä¹Ł
    0.08
    æĺ§
    0.08
    Activations Density 0.233%

    No Known Activations