© 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. 11585
    Prev
    Next
    INDEX
    Explanations

    quicksort partition

    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
    纶
    -0.08
    åħħå®ŀèĩªå·±
    -0.08
    stry
    -0.07
    åĬłçłģ
    -0.07
    Overrides
    -0.07
    gnose
    -0.07
     terg
    -0.07
    oose
    -0.07
    åıłåĬł
    -0.07
    _hid
    -0.07
    POSITIVE LOGITS
     pivot
    0.11
     Pivot
    0.11
    pivot
    0.10
    .pivot
    0.09
     partition
    0.09
     piv
    0.08
     partitions
    0.07
    partition
    0.07
     Partition
    0.07
    å¹³çŃī
    0.07
    Activations Density 0.004%

    No Known Activations