© 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. 47882
    Prev
    Next
    INDEX
    Explanations

    dividing or partitioning along lines

    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
    çªĹåı£
    -0.08
    缴æݥ使çĶ¨
    -0.08
    缴æİ¥ä¸İ
    -0.07
    TemplateName
    -0.07
    _pdata
    -0.07
    è©°
    -0.07
    izedName
    -0.07
    天æŶ
    -0.07
    proc
    -0.07
    atars
    -0.07
    POSITIVE LOGITS
    åĪĨåī²
    0.16
     divides
    0.15
     dividing
    0.14
    åĪĴåĪĨ
    0.14
    åĪĨéļĶ
    0.14
     splits
    0.13
     partitions
    0.13
     splitting
    0.13
     membag
    0.12
     divide
    0.12
    Activations Density 0.026%

    No Known Activations