© 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. 61967
    Prev
    Next
    INDEX
    Explanations

    counting duplicates or identical items

    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
    isso
    -0.08
    auta
    -0.08
    obuf
    -0.08
    åħŃç§į
    -0.08
    anen
    -0.08
    è¢«ä¾ĽåºĶåķĨ
    -0.08
    usso
    -0.07
    ä¸īå®Ŀ
    -0.07
    olucion
    -0.07
    åĩłç§į
    -0.07
    POSITIVE LOGITS
     identical
    0.11
     duplicate
    0.10
    Duplicate
    0.10
    éĩįå¤į
    0.10
     duplicates
    0.10
     duplication
    0.09
    _duplicate
    0.09
     duplicated
    0.09
    duplicate
    0.09
    缸åIJĮçļĦ
    0.09
    Activations Density 0.045%

    No Known Activations