© 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. 39829
    Prev
    Next
    INDEX
    Explanations

    AML SYSTEM

    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
    onne
    -0.07
    建ä¸ļ
    -0.07
    èĽĨ
    -0.07
    天èĬ±
    -0.07
    æ¯Ķå°Ķ
    -0.06
    çĥģ
    -0.06
    gé
    -0.06
    ouch
    -0.06
    åıªç®¡
    -0.06
    æ²īçĿ¡
    -0.06
    POSITIVE LOGITS
    ä¸īéģĵ
    0.08
     pragma
    0.07
    å¦ĤæŀľæĤ¨å¯¹
    0.07
    iaan
    0.07
    ãĤ¦ãĥł
    0.07
    éģĤ
    0.07
    umd
    0.07
    Signatur
    0.07
     continuation
    0.07
    åħ¬æ¼Ķ
    0.07
    Activations Density 0.058%

    No Known Activations