© 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. 39574
    Prev
    Next
    INDEX
    Explanations

    days and dates

    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»İæĹł
    -0.08
    Marks
    -0.07
    èĦļè¸ıå®ŀåľ°
    -0.07
    åĪ¹éĤ£éĹ´
    -0.06
    aby
    -0.06
    iar
    -0.06
    æĩĤå¾ĹäºĨ
    -0.06
    åIJ«èĵĦ
    -0.06
     prag
    -0.06
    .getOwnProperty
    -0.06
    POSITIVE LOGITS
     scheduled
    0.10
    æĹ¥ç¨ĭ
    0.08
     Scheduled
    0.08
    å®ļäºİ
    0.08
    ä¸ĢäºĮ
    0.08
     schedule
    0.08
     planned
    0.08
    åIJįå±±
    0.08
     slated
    0.07
    äºĪå®ļ
    0.07
    Activations Density 0.540%

    No Known Activations