© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28924
    Prev
    Next
    INDEX
    Explanations

    table 1

    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
    个人页
    -0.08
    ywa
    -0.07
    Angular
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.06
    çī
    -0.06
    ÑĩÑĮÑı
    -0.06
    ;;;;;;;;
    -0.06
     ìŀĦ
    -0.06
     Caz
    -0.06
    æĸ©
    -0.06
    POSITIVE LOGITS
    æīĢ示
    0.10
    æĺķ
    0.08
    ç¾İ好çļĦæľªæĿ¥
    0.08
    διά
    0.07
    teen
    0.07
     typeid
    0.07
    ÄĥtÄĥ
    0.07
    table
    0.07
    عÙĬÙĬÙĨ
    0.07
    ÑĢÑĥÑĤ
    0.07
    Activations Density 0.042%

    No Known Activations