© 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. 28409
    Prev
    Next
    INDEX
    Explanations

    CSS, code examples, mathematics

    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
    ArrayOf
    -0.10
    ç¼¥
    -0.09
    intl
    -0.09
    彿
    -0.08
    ipple
    -0.08
    ãģĭãģ¯
    -0.08
    tility
    -0.08
    /respond
    -0.08
    launcher
    -0.08
    翼翼
    -0.08
    POSITIVE LOGITS
    à¹Ģà¸Ĺà¹Īาà¸Ļัà¹īà¸Ļ
    0.08
    æĪijæīį
    0.08
    é²ģ
    0.07
    or
    0.07
     rather
    0.07
    ä»»
    0.07
    æīį
    0.06
     or
    0.06
    æīįä¼ļæľī
    0.06
    æīįè¡Į
    0.06
    Activations Density 0.048%

    No Known Activations