© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12081
    Prev
    Next
    INDEX
    Explanations

    segmentation, split, 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
    oment
    -0.07
     ranking
    -0.07
    ranking
    -0.07
    ç¨ĢéĩĬ
    -0.07
    _accessible
    -0.07
     rank
    -0.07
    ås
    -0.07
    对åIJĦç§į
    -0.06
    ierra
    -0.06
     ram
    -0.06
    POSITIVE LOGITS
    åĪĴåĪĨ
    0.11
    åĪĨ段
    0.11
    åĪĴåĪĨ为
    0.10
     segmentation
    0.09
    åĪĨåī²
    0.09
    Segment
    0.09
    segments
    0.09
    Split
    0.09
    seg
    0.09
    _split
    0.09
    Activations Density 0.008%

    No Known Activations