© 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. 58913
    Prev
    Next
    INDEX
    Explanations

    split, half, sum, 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
    Negative Logits
    bers
    -0.07
    leur
    -0.07
    leurs
    -0.07
    loch
    -0.07
    级åĪ«
    -0.07
    æĮ¤
    -0.07
    ngo
    -0.07
    /id
    -0.06
    aky
    -0.06
    æ··
    -0.06
    POSITIVE LOGITS
    两éĥ¨åĪĨ
    0.12
     halves
    0.11
    åĪĴåĪĨ
    0.10
    ãģ«åĪĨ
    0.10
     splits
    0.10
     splitted
    0.09
    åįĬåĪĨ
    0.09
     Split
    0.09
     splitting
    0.09
    åĪĨåī²
    0.09
    Activations Density 0.032%

    No Known Activations