© 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. 2364
    Prev
    Next
    INDEX
    Explanations

    flips or conversions

    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
    첩
    -0.07
    æĮł
    -0.07
    åĪĨ段
    -0.07
    åį³åĪ°
    -0.07
     reflex
    -0.07
    _multiple
    -0.06
     sema
    -0.06
    aley
    -0.06
    äºĮ次
    -0.06
    åħ¨éĿ¢è´¯å½»èIJ½å®ŀ
    -0.06
    POSITIVE LOGITS
    转åĮĸçļĦ
    0.11
    转åĮĸ
    0.10
     conversions
    0.10
     converting
    0.09
    转åĮĸæĪIJ
    0.09
     internally
    0.09
     Converts
    0.09
     conversion
    0.08
    conversion
    0.08
     converts
    0.08
    Activations Density 0.001%

    No Known Activations