© 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. 49438
    Prev
    Next
    INDEX
    Explanations

    usage and coverage

    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
    ings
    -0.11
    liness
    -0.10
    nya
    -0.10
    ness
    -0.10
    ingly
    -0.09
    å¾Ĺèµ·
    -0.09
    ners
    -0.09
    sson
    -0.09
    å°¼äºļ
    -0.08
    sWith
    -0.08
    POSITIVE LOGITS
    Ùĭ
    0.11
    Ö¼
    0.09
    à¹Į
    0.09
    es
    0.08
    åľ¨
    0.08
    ption
    0.08
    æīĭæľºç«Ļ
    0.08
    ëĤĺë§Ī
    0.08
    Ïĥη
    0.08
    ../../../
    0.08
    Activations Density 0.130%

    No Known Activations