© 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. 49981
    Prev
    Next
    INDEX
    Explanations

    citation prefixes like et al. and [@B]

    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
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    -position
    -0.06
    漫游
    -0.06
    纪åħĥ
    -0.06
    iesel
    -0.06
    MLE
    -0.06
    èĢĮä¸ĭ
    -0.06
    usel
    -0.06
    ippers
    -0.06
    eks
    -0.06
    POSITIVE LOGITS
    大åłĤ
    0.08
    reiz
    0.07
    redo
    0.07
    大潮
    0.07
    utin
    0.07
    鼨ä¸Ń
    0.07
     reb
    0.07
    볤
    0.07
    lus
    0.07
    æľĪåħī
    0.07
    Activations Density 0.268%

    No Known Activations