© 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. 18790
    Prev
    Next
    INDEX
    Explanations

    polynomials

    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
    uids
    -0.09
    wai
    -0.08
    ÙĪØ·
    -0.08
    æ¥ļæ¥ļ
    -0.08
    entic
    -0.08
    erton
    -0.08
    entes
    -0.07
    -caption
    -0.07
    chts
    -0.07
    sequential
    -0.07
    POSITIVE LOGITS
     polynomial
    0.08
    pol
    0.08
    /pol
    0.08
    -pol
    0.07
    ifact
    0.07
     Polynomial
    0.07
    à¸Ĭัà¹īà¸Ļ
    0.06
    ç»ĥ
    0.06
    rette
    0.06
    ä¸įåİĮ
    0.06
    Activations Density 0.006%

    No Known Activations