© 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. 63416
    Prev
    Next
    INDEX
    Explanations

    poisoning and intoxication

    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
    è¥
    -0.08
     Ñģке
    -0.08
    asons
    -0.08
    ä¸įåīį
    -0.08
    atars
    -0.07
     гне
    -0.07
    é»ijçľ¼åľĪ
    -0.07
    èĥİåİĭ
    -0.07
    oren
    -0.07
    oten
    -0.07
    POSITIVE LOGITS
    ä¸Ńæ¯Ĵ
    0.15
     poisoning
    0.14
    æ¯Ĵ
    0.12
     ingestion
    0.12
     toxic
    0.11
    æĹłæ¯Ĵ
    0.11
     overdose
    0.11
     poison
    0.11
     toxicity
    0.10
    解æ¯Ĵ
    0.10
    Activations Density 0.080%

    No Known Activations