© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 6961
    Prev
    Next
    INDEX
    Explanations

    jet mills, ,Button

    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
    Negative Logits
     alike
    -0.07
     Hoe
    -0.06
    aza
    -0.06
     zufolge
    -0.06
    esa
    -0.06
    acky
    -0.06
    /framework
    -0.06
    该款
    -0.06
    ast
    -0.06
    ç³»æķ°
    -0.06
    POSITIVE LOGITS
    uken
    0.08
    ToInt
    0.07
    éľĦ
    0.07
    르íģ¬
    0.07
    OwnProperty
    0.07
    å°Ķå¾·
    0.07
    æĸĹç½Ĺ
    0.07
    ByText
    0.07
    ISING
    0.07
    INCT
    0.07
    Activations Density 0.037%

    No Known Activations