© 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. 26802
    Prev
    Next
    INDEX
    Explanations

    toxic substances or effects

    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
    æŀĿèĬ±
    -0.08
    aland
    -0.08
    ÅŁt
    -0.08
     telef
    -0.07
    اÛĮØ´
    -0.07
    ãģ«ãģĤãĤĭ
    -0.07
    è¤Ĥ
    -0.07
    جرÙĬ
    -0.07
    ä¸ĭåIJĮ
    -0.07
    èĮ¬
    -0.07
    POSITIVE LOGITS
     hại
    0.09
    身亡
    0.09
    ious
    0.08
    à¸ĵุ
    0.08
    æĢ§çļĦ
    0.08
    à¹Īวà¸ĩ
    0.08
    俱åħ¨
    0.08
    ়
    0.08
    æĹłæ¯ĶçļĦ
    0.08
    ogenic
    0.08
    Activations Density 0.039%

    No Known Activations