© 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. 57444
    Prev
    Next
    INDEX
    Explanations

    pronoun "he" followed by a verb

    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
    å²ģå²ģ
    -0.08
    mente
    -0.08
    ly
    -0.07
    reden
    -0.07
    æľī幸
    -0.07
    ALLY
    -0.07
    lyn
    -0.06
    Ùĭا
    -0.06
    reven
    -0.06
    ÑģÑĤвÑĥ
    -0.06
    POSITIVE LOGITS
    /she
    0.11
    'll
    0.11
    ppard
    0.10
    -même
    0.09
    ’ll
    0.09
    zelf
    0.08
    zel
    0.08
    've
    0.08
    avier
    0.08
     ëĺIJíķľ
    0.08
    Activations Density 0.462%

    No Known Activations