© 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. 61431
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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
     only
    -0.08
     hereby
    -0.07
     certainly
    -0.07
     лиÑĪÑĮ
    -0.07
    only
    -0.06
    orem
    -0.06
     infatti
    -0.06
    à¹Ģà¸ŀียà¸ĩ
    -0.06
     often
    -0.06
    1
    -0.06
    POSITIVE LOGITS
    /her
    0.10
    arness
    0.09
    kaar
    0.09
    zelf
    0.09
    ä¸ĭåIJĮ
    0.09
     Ñĥгодно
    0.09
     jeweilige
    0.08
    =='
    0.08
     OTHERWISE
    0.08
    -know
    0.08
    Activations Density 0.310%

    No Known Activations