© 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. 22052
    Prev
    Next
    INDEX
    Explanations

    at least, more than, either

    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
    won
    -0.08
    fera
    -0.08
    FirstResponder
    -0.07
    [](
    -0.07
    ä¹ĭçİĭ
    -0.07
    æľīäºĽäºĭ
    -0.07
    vrier
    -0.07
    Overflow
    -0.07
    éĩľ
    -0.07
    æł¹æľ¬ä¸Ĭ
    -0.07
    POSITIVE LOGITS
    èĩ³å°ij
    0.12
     âī¥
    0.11
     mindestens
    0.10
     EITHER
    0.10
    ä¸įå°ijäºİ
    0.10
     either
    0.09
    èĩ³å°ijæľī
    0.09
    âī¥
    0.09
     almeno
    0.09
    æĪĸèĢħæľī
    0.09
    Activations Density 0.099%

    No Known Activations