© 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. 40028
    Prev
    Next
    INDEX
    Explanations

    new version/types

    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
    annis
    -0.07
    .Transform
    -0.07
    ×ķ×Ĺ
    -0.06
    å°½åħ¶
    -0.06
    POSITE
    -0.06
    äº
    -0.06
    è¾Ĺ
    -0.06
    anh
    -0.06
    èĢį
    -0.06
    æľīåħ¶
    -0.06
    POSITIVE LOGITS
    æĸ°çļĦ
    0.17
     nuevos
    0.16
    æĸ°å¢ŀ
    0.16
     new
    0.16
     nouveaux
    0.15
    æĸ°ãģŁãģ«
    0.15
    æĸ°çļĦä¸Ģ
    0.15
     nuovi
    0.15
     novos
    0.15
     новÑĭÑħ
    0.15
    Activations Density 0.574%

    No Known Activations