© 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. 39560
    Prev
    Next
    INDEX
    Explanations

    reconfigured or referred

    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
    mes
    -0.07
    ...(
    -0.07
    æĺ¯è¿Ļ个
    -0.07
    çľĭåĪ°è¿Ļ个
    -0.07
    æĪijä¸İ
    -0.07
    à¯Īயிலà¯į
    -0.07
    estelle
    -0.07
    اص
    -0.07
    æĪij以
    -0.07
    ÙĬزات
    -0.07
    POSITIVE LOGITS
    ation
    0.07
    áĥIJáĥľ
    0.07
    ତ
    0.07
    ostal
    0.07
    thern
    0.06
    ä»Ĭ天å°ıç¼ĸå°±
    0.06
    ತà³į
    0.06
    æłĩåĩĨè¦ģæ±Ĥ
    0.06
     courtesy
    0.06
     the
    0.06
    Activations Density 0.017%

    No Known Activations