© 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. 34377
    Prev
    Next
    INDEX
    Explanations

    leverage

    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
    verständlich
    -0.09
    翼翼
    -0.09
    -fashioned
    -0.09
    ored
    -0.08
    erton
    -0.08
    ningar
    -0.08
    ãĤ¥
    -0.08
    izen
    -0.08
    OrElse
    -0.07
    æĹłéĹ»
    -0.07
    POSITIVE LOGITS
    ed
    0.11
    ез
    0.09
    aging
    0.09
    fect
    0.09
    er
    0.09
    edin
    0.08
    aged
    0.08
     sầu
    0.08
    eria
    0.08
    force
    0.08
    Activations Density 0.017%

    No Known Activations