© 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. 20167
    Prev
    Next
    INDEX
    Explanations

    adenovirus or virus

    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
    èĬĴ
    -0.07
    éįĬ
    -0.07
    çĤ¼
    -0.07
    人åij½
    -0.07
    大æī¹
    -0.07
    çħ¤æ°Ķ
    -0.06
    æī¹
    -0.06
    çħī
    -0.06
    çĨŁ
    -0.06
    çĦĻ
    -0.06
    POSITIVE LOGITS
     viruses
    0.13
    çĹħæ¯Ĵ
    0.11
     virus
    0.10
    宿
    0.09
    çĹħæ¯ĴçļĦ
    0.09
     viral
    0.09
    ãĤ¦ãĤ¤ãĥ«ãĤ¹
    0.09
    irus
    0.09
     genome
    0.08
     ë°ĶìĿ´ëŁ¬ìĬ¤
    0.08
    Activations Density 0.130%

    No Known Activations