© 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. 46282
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

    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
    究竣
    -0.10
    究竣æĺ¯
    -0.09
    ä½łåĪ°åºķ
    -0.08
    åĪ°åºķ
    -0.08
     tehát
    -0.08
    åĪ°åºķæĺ¯ä»Ģä¹Ī
    -0.07
    åIJīå°Ķ
    -0.07
    åĪ°åºķæĺ¯
    -0.07
    imir
    -0.07
    ä¸Ĭçľĭ
    -0.07
    POSITIVE LOGITS
    occa
    0.09
    hin
    0.07
    ä¹IJäºİåĬ©äºº
    0.07
    éĹ´æİ¥
    0.07
    建平
    0.07
    åĢŁçĿĢ
    0.07
    å®ĥæľī
    0.07
    ibas
    0.07
    åı¯ä»¥éĢļè¿ĩ
    0.07
    ivan
    0.07
    Activations Density 0.060%

    No Known Activations