© 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. 30077
    Prev
    Next
    INDEX
    Explanations

    separating different types or periods

    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
    æĿ¥åĽŀ
    -0.07
    umd
    -0.07
    ars
    -0.07
    ä½ľåģĩ
    -0.07
    unic
    -0.06
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
     Spur
    -0.06
    æºĸ
    -0.06
     bid
    -0.06
    ook
    -0.06
    POSITIVE LOGITS
    åĪĨå¼Ģ
    0.17
     separates
    0.16
     separ
    0.15
     separating
    0.15
    åĪĨ离
    0.15
    Separ
    0.14
     separate
    0.14
     Separ
    0.14
     separated
    0.14
     separation
    0.14
    Activations Density 0.238%

    No Known Activations