© 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. 22862
    Prev
    Next
    INDEX
    Explanations

    derived from

    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
    elsey
    -0.09
    enor
    -0.07
    .libs
    -0.07
    enis
    -0.07
     wyn
    -0.07
    ä¸įå¾Ĺ
    -0.07
    à¸ļาล
    -0.07
    æĹ¥ä¸ĬåįĪ
    -0.07
    vene
    -0.07
    åĴĮåķĨä¸ļ
    -0.06
    POSITIVE LOGITS
    æ½ľåľ¨çļĦ
    0.07
    æĶ¹çīĪ
    0.07
    _attrs
    0.06
    اÙħت
    0.06
    _ATTRIBUTES
    0.06
    Apps
    0.06
    æ¸ħæ¥ļæ¥ļ
    0.06
    Attributes
    0.06
    TRS
    0.06
    çįħåŃIJ
    0.06
    Activations Density 0.004%

    No Known Activations