© 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. 10511
    Prev
    Next
    INDEX
    Explanations

    bounds, bounded, bound

    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
    çİ®
    -0.08
    estad
    -0.08
    ampe
    -0.07
    coration
    -0.07
    åħŃæĪIJ
    -0.07
    ×Ļת×Ķ
    -0.07
    注æĦıçļĦæĺ¯
    -0.07
    æĬĺ
    -0.07
    ä¸ĥæĪIJ
    -0.07
    TRI
    -0.07
    POSITIVE LOGITS
    æľĢå¤ļ
    0.09
     bounded
    0.09
    Bound
    0.09
    åºĶ该ä¸įä¼ļ
    0.09
    bound
    0.08
    bounded
    0.08
     bound
    0.08
     bounds
    0.08
    æĹłèĻij
    0.08
    _max
    0.07
    Activations Density 0.019%

    No Known Activations