© 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. 43801
    Prev
    Next
    INDEX
    Explanations

    comparisons involving "than"

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.11
    èݱæĸ¯
    -0.10
    ippo
    -0.09
    erdale
    -0.09
    tee
    -0.08
    sWith
    -0.08
    VERY
    -0.08
    تÙĬÙĨ
    -0.08
    å¸Īé£İ
    -0.08
    odiac
    -0.08
    POSITIVE LOGITS
    -needed
    0.09
     those
    0.07
     usual
    0.07
    soever
    0.07
     any
    0.07
    ¯
    0.07
    ault
    0.07
    -ever
    0.07
     ours
    0.07
    ÑĪний
    0.07
    Activations Density 0.079%

    No Known Activations