© 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. 15629
    Prev
    Next
    INDEX
    Explanations

    toxic substances or dangerous products

    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
    çī¹åĪ«æĺ¯
    -0.09
    å°¤åħ¶æĺ¯
    -0.08
    '[
    -0.07
    çī¹åĪ«æĺ¯åľ¨
    -0.07
    ettel
    -0.07
    ':
    -0.07
    å¸Ĥéķĩ
    -0.07
    -/
    -0.07
     Brus
    -0.07
    çĮ´
    -0.07
    POSITIVE LOGITS
    æĶ¶èİ·çļĦ
    0.07
    缺ä¸Ģ
    0.07
    å°±æĺ¯æĪij们çļĦ
    0.07
    ì·¨
    0.07
    绣ä¸Ģéĥ¨ç½²
    0.07
     starring
    0.07
    å°±æĺ¯æľĢ好çļĦ
    0.06
    ĩ´
    0.06
    é£ŀè¿ĩ
    0.06
    imson
    0.06
    Activations Density 0.002%

    No Known Activations