© 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. 23108
    Prev
    Next
    INDEX
    Explanations

    A -> B notation

    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
     Stol
    -0.08
    ellis
    -0.07
    è´¥
    -0.07
    iley
    -0.07
    jure
    -0.07
    uzzi
    -0.07
    urai
    -0.07
     incol
    -0.07
    .ravel
    -0.06
    éĩijå®Ŀ
    -0.06
    POSITIVE LOGITS
    enaar
    0.07
    æŁIJ
    0.07
    pok
    0.07
    AAAA
    0.07
    ť
    0.06
    XYZ
    0.06
    YG
    0.06
     XYZ
    0.06
    ebra
    0.06
    æŁIJä¸Ģ天
    0.06
    Activations Density 0.104%

    No Known Activations