© 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. 17751
    Prev
    Next
    INDEX
    Explanations

    configuration settings

    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
    isar
    -0.08
    çŁ
    -0.07
    åĪ·
    -0.07
    egin
    -0.07
     latin
    -0.07
    åĨ¥
    -0.07
    åĨ²
    -0.07
    :disable
    -0.07
    æĸŃ
    -0.07
     Matcher
    -0.07
    POSITIVE LOGITS
    ARES
    0.07
     anges
    0.07
    æīĢ以她
    0.07
    çħ§çĿĢ
    0.06
    çļĦéĿ¢
    0.06
     заÑģе
    0.06
    åĽłèĢĮ
    0.06
    åİ»åIJ§
    0.06
    åĤ¬çĶŁ
    0.06
     joten
    0.06
    Activations Density 0.141%

    No Known Activations