© 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. 7351
    Prev
    Next
    INDEX
    Explanations

    approximate errors or tolerance

    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
    Ŀ¼
    -0.08
    idges
    -0.08
    stile
    -0.07
    iere
    -0.07
    æµĵåİļ
    -0.07
    enius
    -0.07
    Ñģни
    -0.07
    ujan
    -0.07
    STYPE
    -0.07
    赢家
    -0.07
    POSITIVE LOGITS
    误差
    0.11
    æİ¥è¿ij
    0.09
    phant
    0.09
     errors
    0.08
    /close
    0.08
     approximate
    0.08
     near
    0.07
    è¿ijä¼¼
    0.07
    误
    0.07
     tolerance
    0.07
    Activations Density 0.034%

    No Known Activations