© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10722
    Prev
    Next
    INDEX
    Explanations

    you referring to

    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
    ä»ĸ认为
    -0.08
    azion
    -0.08
    èĤ¡ä¸ľåıĬ
    -0.08
    annes
    -0.08
    unsupported
    -0.08
    าราà¸ĩ
    -0.08
    ä»ĸä»İ
    -0.07
    ä»ĸ没æľī
    -0.07
    _UNSUPPORTED
    -0.07
    imbledon
    -0.07
    POSITIVE LOGITS
     specifically
    0.08
    igh
    0.07
    ä¸į欲
    0.07
    æľĽ
    0.06
     hẳn
    0.06
    æĪĸ许
    0.06
     situ
    0.06
    举ä¸Ģåıįä¸ī
    0.06
    æ²īé»ĺ
    0.06
    åı¯èĥ½ä¼ļ
    0.06
    Activations Density 0.004%

    No Known Activations