© 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. 42535
    Prev
    Next
    INDEX
    Explanations

    convert/redirect/expand/animation/relief/hide/tour

    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
    è´£ç¼ĸ
    -0.07
    å®Ł
    -0.07
    æķĻçłĶ室
    -0.06
    olume
    -0.06
    ç£Ĭ
    -0.06
    æĬ¥è®°èĢħ
    -0.06
    lda
    -0.06
    ETTA
    -0.06
    ürg
    -0.06
    æĶ¾å¿ĥçļĦ
    -0.06
    POSITIVE LOGITS
    aro
    0.08
    åıªæľīä¸Ģ次
    0.08
    aar
    0.08
    è¿ĩä¸Ģ次
    0.08
    ä¸Ģ次
    0.08
    yun
    0.07
    ken
    0.07
    ä¹Łåıª
    0.07
    äºĨä¸Ģ次
    0.07
    ä¸ĢåĽŀ
    0.07
    Activations Density 0.018%

    No Known Activations