© 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. 57191
    Prev
    Next
    INDEX
    Explanations

    cyanide or azide containing groups

    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
    ç¨Ģçĸı
    -0.07
     coarse
    -0.07
    äºı
    -0.07
    æ¯Ľ
    -0.07
    æ¶ĪéĢĢ
    -0.07
    çļĦçĶŁæ´»ä¸Ń
    -0.07
    خر
    -0.07
    ç³»
    -0.07
    ÑĪке
    -0.06
     fur
    -0.06
    POSITIVE LOGITS
    åı¦ä¸Ģ端
    0.08
    两端
    0.08
    reverse
    0.08
    ãĥĸãĥĥãĤ¯
    0.08
    atrix
    0.07
    ingkat
    0.07
    ationally
    0.07
     reverse
    0.07
    arli
    0.07
     Reverse
    0.07
    Activations Density 0.005%

    No Known Activations