© 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. 23142
    Prev
    Next
    INDEX
    Explanations

    affiliation

    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
    å°ļ
    -0.07
    åħĪæĿ¥
    -0.07
    unker
    -0.06
    éĢļ常为
    -0.06
    主è¦ģä»İäºĭ
    -0.06
    itiv
    -0.06
    esis
    -0.06
    aki
    -0.06
    çĤ¹èµŀ
    -0.06
    akai
    -0.06
    POSITIVE LOGITS
    管çIJĨæĸ¹éĿ¢
    0.09
    waran
    0.08
    åħ³äºİ
    0.08
    omnia
    0.08
    ieni
    0.07
     omitted
    0.07
     regarding
    0.07
    åIJİéĿ¢çļĦ
    0.07
     omission
    0.07
    ä¸Ĭæīĭ
    0.07
    Activations Density 0.148%

    No Known Activations