© 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. 20989
    Prev
    Next
    INDEX
    Explanations

    MEMORANDUM

    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
    ä¿±è¿Ľ
    -0.08
    ringe
    -0.07
    ipple
    -0.07
    亲亲
    -0.07
    个ç¨İ
    -0.07
    ukan
    -0.07
    oli
    -0.06
    ä½łæĺ¯è°ģ
    -0.06
    PLE
    -0.06
    éİ®
    -0.06
    POSITIVE LOGITS
    ä¸ĸçķĮ第ä¸Ģ
    0.08
    èIJĦ
    0.07
    LEASE
    0.07
    åĮ£
    0.07
     Westbrook
    0.07
    oghi
    0.07
    ¾
    0.06
    à´³àµįà´³
    0.06
    åĮħæĭ¬äºĨ
    0.06
     обÑı
    0.06
    Activations Density 0.031%

    No Known Activations