© 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. 58011
    Prev
    Next
    INDEX
    Explanations

    quotations and punctuation

    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
    ваÑĩ
    -0.08
     assignable
    -0.07
    ãģįãģ®
    -0.07
     berupa
    -0.07
     realised
    -0.07
     happening
    -0.07
     proceeding
    -0.07
    à¹īาà¸Ļ
    -0.07
    èĬ±äºĨ
    -0.07
    atables
    -0.07
    POSITIVE LOGITS
    å¿«åľ°
    0.09
    ificantly
    0.09
    edly
    0.09
    lessly
    0.09
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.08
    æĦıè¯Ĩåľ°
    0.08
    æĢ§åľ°
    0.08
    orarily
    0.08
    atively
    0.08
    ographically
    0.08
    Activations Density 0.268%

    No Known Activations