© 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. 47266
    Prev
    Next
    INDEX
    Explanations

    duplicate records or 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
    ulu
    -0.08
    ulat
    -0.08
    nova
    -0.08
    ulai
    -0.08
    agnostics
    -0.08
    ãģ£ãģ±
    -0.07
    emean
    -0.07
    lát
    -0.07
    èı²å°Ķå¾·
    -0.07
    kowski
    -0.07
    POSITIVE LOGITS
     duplication
    0.08
    /cop
    0.08
    æĪĸå¤ļ
    0.08
    缸åIJĮ
    0.08
     nhau
    0.07
    éĩįå¤į
    0.07
    /conf
    0.07
    duplicate
    0.07
    undes
    0.07
     identical
    0.07
    Activations Density 0.087%

    No Known Activations