© 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. 31158
    Prev
    Next
    INDEX
    Explanations

    systematic errors and biases

    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
    _sparse
    -0.08
    itura
    -0.08
    æļĤè¡Į
    -0.08
    ordes
    -0.08
     ëĭ´
    -0.08
    sparse
    -0.07
    kering
    -0.07
     Consort
    -0.07
    áĥĶáĥľ
    -0.07
    ä¹ĭ乡
    -0.07
    POSITIVE LOGITS
     bias
    0.12
    Bias
    0.11
     biases
    0.10
     Bias
    0.10
    åģı
    0.10
    bias
    0.10
    åģıå·®
    0.10
    åģıåIJij
    0.09
    åģı移
    0.08
    åģıé«ĺ
    0.08
    Activations Density 0.006%

    No Known Activations