© 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. 17765
    Prev
    Next
    INDEX
    Explanations

    toxicity of EG and methanol poisoning

    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
    èĴĤæĸ¯
    -0.07
    æŃ£å¸¸
    -0.07
    иден
    -0.06
    ä¸Ģåıį
    -0.06
    bezieh
    -0.06
     wired
    -0.06
     Rivers
    -0.06
    æĬ½çŃĭ
    -0.06
    iffin
    -0.06
    åĨįæİ¥åĨį
    -0.06
    POSITIVE LOGITS
    宿
    0.09
    ä¹ĭæ°Ķ
    0.08
    ä¹ĭçī©
    0.08
    æľ¬åŃ£
    0.08
    æľīå½¢
    0.08
    æĹ©æĬ¥
    0.07
    æģº
    0.07
     локали
    0.07
     lodged
    0.07
     Merr
    0.07
    Activations Density 0.002%

    No Known Activations