© 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. 51018
    Prev
    Next
    INDEX
    Explanations

    pretense or hypocrisy

    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
    ogna
    -0.08
    满æĦı
    -0.08
    -scripts
    -0.07
    thon
    -0.07
    ä¸įä¼ļåĨį
    -0.07
    åĪ«åĨį
    -0.07
    Ãłnh
    -0.07
    åı¯è§Ĥ
    -0.07
    满足äºĨ
    -0.07
    мей
    -0.07
    POSITIVE LOGITS
    caras
    0.07
    ariat
    0.07
    ár
    0.06
    گز
    0.06
    deps
    0.06
     definir
    0.06
    ÑĢек
    0.06
    latin
    0.06
    大åѦçĶŁæ´»
    0.06
    çĶŁæ´»çĶ¨åĵģ
    0.06
    Activations Density 0.002%

    No Known Activations