© 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. 1123
    Prev
    Next
    INDEX
    Explanations

    reductive reduction

    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
    ularity
    -0.08
    жиÑĤ
    -0.07
    maÃŁen
    -0.07
    zar
    -0.07
    åĨħå¤ĸ
    -0.07
    涨äºĨ
    -0.07
    issing
    -0.07
    微信æī«çłģ
    -0.06
    ups
    -0.06
    ration
    -0.06
    POSITIVE LOGITS
    æľīç¦ı
    0.09
    天马
    0.08
     spod
    0.07
    aries
    0.07
    oxy
    0.07
    ÙĪض
    0.07
    รืà¹Īà¸Ļ
    0.07
    åĴĮä¿ĿæĬ¤
    0.07
    çĪµ
    0.07
    eksi
    0.07
    Activations Density 0.015%

    No Known Activations