© 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. 61755
    Prev
    Next
    INDEX
    Explanations

    voltage divider, wheatstone bridge

    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
    æĿ¡
    -0.07
    追踪
    -0.07
    éĽĨä¸Ń
    -0.07
    离æĪij们
    -0.06
    é©°éªĭ
    -0.06
    éĽĨä¸ŃçļĦ
    -0.06
    ombe
    -0.06
    追
    -0.06
    ç°ĩ
    -0.06
     aggregated
    -0.06
    POSITIVE LOGITS
     divider
    0.10
     Ratio
    0.09
     ratios
    0.09
     ratio
    0.09
    æ¯Ķä¾ĭçļĦ
    0.09
    æ¯Ķä¾ĭ
    0.09
    enius
    0.09
    ratio
    0.08
     Divider
    0.08
    akeup
    0.08
    Activations Density 0.008%

    No Known Activations