© 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. 39848
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations

    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
    æľī声
    -0.07
    æĹłåıį
    -0.07
    abox
    -0.07
    MEA
    -0.07
    åľ¨åľ°ä¸Ĭ
    -0.07
    icom
    -0.07
    icast
    -0.07
    Õ¯
    -0.07
    tru
    -0.07
    족
    -0.07
    POSITIVE LOGITS
    ullo
    0.08
    çļĦä½ľåĵģ
    0.07
    quina
    0.07
    ozy
    0.07
    Reserved
    0.07
    çĶµåĮĸåѦ
    0.06
    åľĪåŃIJ
    0.06
    æ°ij
    0.06
    ALLE
    0.06
    ä½į次
    0.06
    Activations Density 0.002%

    No Known Activations