© 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. 21088
    Prev
    Next
    INDEX
    Explanations

    1. INTRODUCTION

    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
    ansen
    -0.10
    æ·Ģ
    -0.09
    çĻ½å¤ľ
    -0.09
    веÑĢи
    -0.08
    reno
    -0.08
    ä»ĭçŁ³
    -0.08
     brac
    -0.08
    秧
    -0.08
    ÑĢÑij
    -0.08
    æĪijåĴĮå¦Īå¦Ī
    -0.08
    POSITIVE LOGITS
    ç¦ģ
    0.06
     SET
    0.06
    SET
    0.06
     HBO
    0.06
    çĽij
    0.06
    gar
    0.06
    (
    0.06
    ç¼ĸç»ĩ
    0.06
    ä¸ĵæľī
    0.06
     j
    0.06
    Activations Density 0.083%

    No Known Activations