© 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. 33646
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions like but/however

    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
    lord
    -0.08
    çļĦä¸Ģå®ļ
    -0.07
    outu
    -0.07
    æĪijåĨ³å®ļ
    -0.07
    untas
    -0.07
    lje
    -0.07
    ä½Ĩæĺ¯åĽłä¸º
    -0.07
    rau
    -0.07
    ibert
    -0.07
    ä½Ĩæĺ¯çĶ±äºİ
    -0.07
    POSITIVE LOGITS
    åݻ年
    0.07
    ornings
    0.07
    ights
    0.07
    ounding
    0.07
    åºŃ
    0.07
    æŃ£æĺ¯
    0.07
    å¹´æĿ¥
    0.07
    å·²åľ¨
    0.07
    usercontent
    0.07
    ~~~~~~~~~~~~~~~~
    0.07
    Activations Density 0.005%

    No Known Activations