© 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. 31652
    Prev
    Next
    INDEX
    Explanations

    related to

    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
    çľ¼ä¸ŃçļĦ
    -0.08
    ä¸įæ±Ĥ
    -0.08
    éģĵæĿ¥
    -0.07
    ìķ
    -0.07
    uisse
    -0.07
    ué
    -0.07
    +offset
    -0.07
    ÙİÙĪÙĴ
    -0.07
    дже
    -0.07
     scrut
    -0.07
    POSITIVE LOGITS
     erat
    0.11
    åĪĩ身åĪ©çĽĬ
    0.08
    à¸ģัà¸ļà¸ģาร
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
     notions
    0.07
    äºİä¸Ģ
    0.07
    gether
    0.07
     closely
    0.07
    å¯ĨåĪĩ
    0.07
    æŃ»äºº
    0.07
    Activations Density 0.214%

    No Known Activations