© 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. 55305
    Prev
    Next
    INDEX
    Explanations

    two things compared

    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
    enso
    -0.09
    潺
    -0.08
    лаго
    -0.08
    à¥Ģल
    -0.07
    erland
    -0.07
    бан
    -0.07
    ä¸İåħ¶å®ĥ
    -0.07
    大æĬĬ
    -0.07
    laus
    -0.07
     cors
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.09
    室éĩĮ
    0.08
     non
    0.08
    ä¸į缸
    0.07
     mutually
    0.07
    æĪĸå¤ļ
    0.06
    è¾īæĺł
    0.06
    åIJĮ
    0.06
     similarly
    0.06
    åIJĮ为
    0.06
    Activations Density 0.047%

    No Known Activations