© 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. 14542
    Prev
    Next
    INDEX
    Explanations

    disease

    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
    ÙĨÚ¯
    -0.08
    åĭī
    -0.07
    æľį
    -0.07
    здÑĢа
    -0.07
     SearchResult
    -0.07
    å¿ĥäºĭ
    -0.07
    èĻĶ
    -0.06
    çĻĤ
    -0.06
    à¸Ľà¸£à¸¸à¸ĩ
    -0.06
    åģ¿
    -0.06
    POSITIVE LOGITS
    ä¸İä¼łç»Ł
    0.07
    ä¸ĸçķĮä¸ĬæľĢ大çļĦ
    0.07
     Thousand
    0.07
    ChangeListener
    0.07
    glas
    0.07
    icen
    0.06
    ç½ijé¦ĸ页
    0.06
    _func
    0.06
    çģ«è½¦ç¥¨
    0.06
    ive
    0.06
    Activations Density 2.308%

    No Known Activations