© 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. 49156
    Prev
    Next
    INDEX
    Explanations

    code structure with errors

    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
    ä¸Ĭè¡Į
    -0.07
    ä¸ĢåŃĹ
    -0.07
    æļĤ
    -0.06
    ÙĪÙħ
    -0.06
    atur
    -0.06
     -
    -0.06
     Lowe
    -0.06
    iber
    -0.06
    丼çĶŁ
    -0.06
    mit
    -0.06
    POSITIVE LOGITS
    xab
    0.08
    lotte
    0.08
    æī¾åĽŀå¯Ĩçłģ
    0.08
    INAN
    0.08
    IEWS
    0.08
     anonim
    0.08
    inky
    0.08
    ÃĹ</
    0.07
    ุà¹Īà¸Ļ
    0.07
    indet
    0.07
    Activations Density 0.001%

    No Known Activations