© 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. 14583
    Prev
    Next
    INDEX
    Explanations

    contrasting or ironic messages

    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
     Basic
    -0.08
     basic
    -0.07
     basics
    -0.07
    åIJ¼
    -0.06
    åIJĦå¼ı
    -0.06
    çļĦåŁºæľ¬
    -0.06
    åİŁåĪĻä¸Ĭ
    -0.06
    å¹³æķ´
    -0.06
    _based
    -0.06
    Basic
    -0.06
    POSITIVE LOGITS
    æīĭæ³ķ
    0.11
     juxtap
    0.10
    çļĦæīĭæ³ķ
    0.09
     contrast
    0.09
     subtle
    0.09
     subtly
    0.09
     contrasts
    0.09
     конÑĤÑĢа
    0.09
    贯穿
    0.09
     fo
    0.09
    Activations Density 0.049%

    No Known Activations