© 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. 41446
    Prev
    Next
    INDEX
    Explanations

    specific groups of people

    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
    à¹Ģà¸Ĺียม
    -0.07
    çĵ¶åŃIJ
    -0.07
    对çĻ½
    -0.07
    FieldValue
    -0.07
    اÙħÙĦ
    -0.07
    èĬ·
    -0.07
    edale
    -0.07
    èĺĭ
    -0.07
     getField
    -0.07
    åħ³æ³¨æĪij们
    -0.07
    POSITIVE LOGITS
    åıªè¦ģæĺ¯
    0.08
    æĺİæĺİæĺ¯
    0.08
    çļĦéĿŀ
    0.08
    èĻ½çĦ¶æĺ¯
    0.08
    åIJĮ为
    0.07
     berbahan
    0.07
    å¦Ĥæŀľæĺ¯
    0.07
    ä¸į管
    0.07
    èĻ½æĺ¯
    0.07
    å±ŀ
    0.07
    Activations Density 0.463%

    No Known Activations