© 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. 57313
    Prev
    Next
    INDEX
    Explanations

    measurement tolerance and error

    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
    ukum
    -0.09
    inach
    -0.08
    croft
    -0.08
    è¿ĩå¤ļ
    -0.08
    elp
    -0.08
    enen
    -0.08
    eliz
    -0.08
    并éĿŀæĺ¯
    -0.08
    anni
    -0.08
    istan
    -0.08
    POSITIVE LOGITS
    误差
    0.10
     errors
    0.10
     accuracy
    0.09
     error
    0.09
     accur
    0.08
     Errors
    0.07
     erreur
    0.07
     errori
    0.07
    精度
    0.07
     errs
    0.07
    Activations Density 0.050%

    No Known Activations