© 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. 26900
    Prev
    Next
    INDEX
    Explanations

    death, dying, suicide, martyrdom

    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
    æıIJéĺ²
    -0.07
    她çİ°åľ¨
    -0.07
    åģĩæĹ¥
    -0.07
    ä»ij
    -0.07
    ساÙĨÛĮ
    -0.06
    大çīĮ
    -0.06
    //
    -0.06
    注æĦıäºĨ
    -0.06
     magia
    -0.06
    çŃĴ
    -0.06
    POSITIVE LOGITS
    æ®ī
    0.10
    æŃ»çļĦ
    0.09
    æŃ»åIJİ
    0.09
    èĢĮæŃ»
    0.09
    æĹłæĢ¨æĹłæĤĶ
    0.09
    临ç»Ī
    0.09
    åħīèį£
    0.08
    æŃ»ä¸į
    0.08
    以身
    0.08
    æĹłæĢ¨
    0.08
    Activations Density 0.058%

    No Known Activations