© 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. 41706
    Prev
    Next
    INDEX
    Explanations

    adjective followed by pronoun/article

    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
    æŶéĹ´åľ¨
    -0.07
    ÑĩеÑĢед
    -0.07
    ovacÃŃ
    -0.07
     ÙĨکرد
    -0.07
    oli
    -0.07
    оÑģÑĮ
    -0.07
    çŃīåľ¨
    -0.07
    anning
    -0.07
    ivanje
    -0.07
     اÛĮÙĨÚ©Ùĩ
    -0.07
    POSITIVE LOGITS
    .htm
    0.08
    .dart
    0.07
    éĴ±äºĨ
    0.07
    ayed
    0.07
     is
    0.07
     zuk
    0.07
    ändig
    0.07
     exist
    0.07
    >()
    0.07
    emas
    0.07
    Activations Density 0.031%

    No Known Activations