© 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. 24459
    Prev
    Next
    INDEX
    Explanations

    editing, manipulation, modification

    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
    erst
    -0.08
    abel
    -0.07
    hc
    -0.07
     cal
    -0.07
    海天
    -0.07
    hle
    -0.07
    èݱæĸ¯
    -0.07
    æĿIJæĸĻä¸İ
    -0.07
     NDEBUG
    -0.06
    hek
    -0.06
    POSITIVE LOGITS
    çī¡
    0.08
    eteor
    0.07
    oud
    0.07
    asar
    0.07
    åIJİåĨį
    0.07
    漫游
    0.07
     Modification
    0.07
     Merrill
    0.07
     boarded
    0.06
    æij©æł¹
    0.06
    Activations Density 0.100%

    No Known Activations