© 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. 2549
    Prev
    Next
    INDEX
    Explanations

    report titles

    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
    anze
    -0.07
    æĪĸèĢħåħ¶ä»ĸ
    -0.07
    zony
    -0.07
    opin
    -0.06
    ancia
    -0.06
     other
    -0.06
    asher
    -0.06
    éĤ£æŶçļĦ
    -0.06
    eko
    -0.06
    ÙĪرÙĥ
    -0.06
    POSITIVE LOGITS
    ادر
    0.07
    æľīæѤ
    0.07
    ibar
    0.07
    wai
    0.07
    ãĤ¡
    0.07
    ä¸ļåįıä¼ļ
    0.07
    eneg
    0.07
    uve
    0.07
    Carthy
    0.07
    pers
    0.07
    Activations Density 0.002%

    No Known Activations