© 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. 43390
    Prev
    Next
    INDEX
    Explanations

    additional information and constraints

    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
    _MAJOR
    -0.08
     ëĮĢë¹Ħ
    -0.08
    æľ¬ç½ij
    -0.08
    اÙĪر
    -0.08
    带ä¸Ĭ
    -0.07
    å¼ĢçªĹ
    -0.07
    ename
    -0.07
    æĽ¿ãģĪ
    -0.07
    bjerg
    -0.07
    boom
    -0.07
    POSITIVE LOGITS
     additional
    0.11
    约æĿŁ
    0.11
     Additional
    0.10
    additional
    0.10
    Additional
    0.09
     constraints
    0.09
    é¢Ŀå¤ĸçļĦ
    0.09
     constraint
    0.09
     dodatkowe
    0.09
     rÃłng
    0.08
    Activations Density 0.011%

    No Known Activations