© 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. 3239
    Prev
    Next
    INDEX
    Explanations

    animal diseases

    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
    neh
    -0.07
    éļıçĿĢ社ä¼ļ
    -0.07
    iming
    -0.07
    åı¯å¾ª
    -0.06
     Warszaw
    -0.06
    erez
    -0.06
    ays
    -0.06
    è¦ģæ±Ĥèĩªå·±
    -0.06
    zed
    -0.06
     Sov
    -0.06
    POSITIVE LOGITS
     susceptible
    0.10
     host
    0.09
     hosts
    0.09
    hosts
    0.09
    åıĹ害
    0.09
    宿主
    0.09
    sus
    0.09
     suspected
    0.08
     susceptibility
    0.08
     unsus
    0.08
    Activations Density 0.332%

    No Known Activations