© 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. 8801
    Prev
    Next
    INDEX
    Explanations

    and or lists

    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
    ajari
    -0.07
    enan
    -0.07
    æīģ
    -0.07
    ides
    -0.07
    inery
    -0.07
    dah
    -0.07
     Miner
    -0.07
    cade
    -0.06
    adian
    -0.06
    ¿
    -0.06
    POSITIVE LOGITS
    yı
    0.08
     Vest
    0.07
    ัà¸Ļ
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    家éŨåı£
    0.07
    .StackTrace
    0.07
    çļĦä¸Ģç»Ħ
    0.07
    éĽĨåĽ¢åľ¨
    0.07
    è¦ģæ±Ĥåľ¨
    0.06
    她便
    0.06
    Activations Density 0.174%

    No Known Activations