© 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. 45548
    Prev
    Next
    INDEX
    Explanations

    disasters, emergencies, conflicts

    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
    æģ¼
    -0.09
    梢
    -0.07
    ivr
    -0.07
    å®
    -0.07
    æĹ¥æ¸IJ
    -0.07
    ãģĦãĤı
    -0.07
    Primitive
    -0.07
    èĩªå¼º
    -0.07
    æµĵæµĵ
    -0.06
    ä¸ĥçĻ¾
    -0.06
    POSITIVE LOGITS
    å½ĵå¹´çļĦ
    0.12
    åİĨåı²ä¸ĬçļĦ
    0.11
    å½ĵå¹´
    0.11
     historically
    0.11
    åİĨåı²ä¸Ĭ
    0.10
    éĩį大
    0.10
    æ¯ıå½ĵ
    0.10
    çŃīéĩį大
    0.10
    çķ¶å¹´
    0.10
    å¾Ģå¾Ģæĺ¯
    0.09
    Activations Density 0.323%

    No Known Activations