© 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. 13856
    Prev
    Next
    INDEX
    Explanations

    excessive

    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
    schaft
    -0.08
    æĪIJç«ł
    -0.08
    acific
    -0.08
    sched
    -0.07
    à¥įस
    -0.07
    å¤ĸ滩
    -0.07
    ján
    -0.07
     elusive
    -0.07
    大æĭĽ
    -0.07
    è¯Ģ
    -0.07
    POSITIVE LOGITS
    ively
    0.09
    iveness
    0.09
    alous
    0.08
    -vous
    0.08
    mente
    0.08
    ious
    0.07
     amounts
    0.07
    plorer
    0.07
    ive
    0.07
    çĻ»å½ķåIJİ
    0.07
    Activations Density 0.006%

    No Known Activations