© 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. 13145
    Prev
    Next
    INDEX
    Explanations

    orientalist attitudes

    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
    ä¸įæĹ©
    -0.07
    opor
    -0.07
     Contr
    -0.06
    .mac
    -0.06
    leccion
    -0.06
    oping
    -0.06
     Partial
    -0.06
     contrac
    -0.06
    ä¸Ģ鸣
    -0.06
    spr
    -0.06
    POSITIVE LOGITS
    è¦ģ被
    0.11
     ÑıкобÑĭ
    0.09
     expend
    0.09
    被è§Ĩ为
    0.09
     perceived
    0.09
     verme
    0.08
    å°±ä¼ļ被
    0.08
    ä¹ħä¹ĭ
    0.08
    èĢĮ被
    0.08
    ä¸ĢæĹ¦è¢«
    0.08
    Activations Density 0.169%

    No Known Activations