© 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. 42697
    Prev
    Next
    INDEX
    Explanations

    customer checks

    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
    ears
    -0.08
     Hels
    -0.07
    /licenses
    -0.07
    åIJīæĸ¯
    -0.07
    éĺĶ
    -0.07
    庵
    -0.07
    à¹ģล
    -0.07
    åĽłä¸ºæľīäºĨ
    -0.07
    encion
    -0.07
    oco
    -0.06
    POSITIVE LOGITS
    è£ģå®ļ
    0.07
    ä¼ļåıijçĶŁ
    0.07
    æ°´çģ«
    0.07
    ä¼Ļ
    0.07
    subclass
    0.07
    çIJĨ论ä¸İ
    0.06
    stel
    0.06
    çIJĨ论ä¸İå®ŀè·µ
    0.06
     AUT
    0.06
    ụng
    0.06
    Activations Density 0.001%

    No Known Activations