© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58844
    Prev
    Next
    INDEX
    Explanations

    partition and grouping

    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
    RequestMethod
    -0.08
    evo
    -0.07
    illard
    -0.07
    OutOfRangeException
    -0.07
    legg
    -0.07
    uwe
    -0.07
    åijķ
    -0.07
    缺
    -0.07
    æ²½
    -0.07
    ANDLE
    -0.07
    POSITIVE LOGITS
     partitions
    0.09
     partition
    0.09
    åĪĴåĪĨ
    0.08
    åĪĨç»Ħ
    0.08
     divides
    0.08
     grouping
    0.08
    åĪĨåĮº
    0.08
    Partition
    0.08
     bund
    0.08
     Partition
    0.08
    Activations Density 0.011%

    No Known Activations