© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17237
    Prev
    Next
    INDEX
    Explanations

    code blocks and keywords

    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
    çļĦä¸Ģ个éĩįè¦ģ
    -0.08
    èĢĮ产çĶŁ
    -0.07
    ophone
    -0.07
    irman
    -0.07
    iro
    -0.07
    foy
    -0.07
    顾åIJįæĢĿ
    -0.07
    积æŀģåIJijä¸Ĭ
    -0.07
     totiž
    -0.07
    èĢĮ产çĶŁçļĦ
    -0.07
    POSITIVE LOGITS
    ï½ŀãĢĤ
    0.09
    );}
    0.08
    {//
    0.07
    æĬ±
    0.07
     ]);
    0.07
    âĢ¦ãĢĤ
    0.07
    åŃļ
    0.07
    {}.
    0.07
    彤
    0.07
     ?.
    0.06
    Activations Density 0.060%

    No Known Activations