© 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. 19712
    Prev
    Next
    INDEX
    Explanations

    confidence intervals and 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
    urf
    -0.07
    master
    -0.07
    surf
    -0.06
     overhead
    -0.06
     superficial
    -0.06
    æĸĹ
    -0.06
    (strict
    -0.06
    _surf
    -0.06
    ä¸įåıĤä¸İ
    -0.06
     повеÑĢÑħноÑģÑĤ
    -0.06
    POSITIVE LOGITS
    å¿ĹåĪļ
    0.09
    credible
    0.08
    Ranges
    0.08
    èĮĥåĽ´åĨħ
    0.08
    èĮĥåĽ´
    0.08
     subrange
    0.08
    èĮĥåĽ´ä¸º
    0.08
     confidently
    0.08
     confidence
    0.08
    ä¿¡å¿ĥçļĦ
    0.08
    Activations Density 0.005%

    No Known Activations