© 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. 32942
    Prev
    Next
    INDEX
    Explanations

    compliment"

    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
    æĹ©å°±
    -0.07
    į
    -0.07
    uren
    -0.07
    踵
    -0.07
    abord
    -0.06
    æĹ©åľ¨
    -0.06
    _fatal
    -0.06
    agre
    -0.06
    ->$
    -0.06
     tardi
    -0.06
    POSITIVE LOGITS
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.13
     supposedly
    0.13
     nomin
    0.12
    ä½Ĩåħ¶å®ŀ
    0.12
     truly
    0.12
     ostensibly
    0.11
    å®ŀåĪĻ
    0.11
     Truly
    0.11
    çľĭä¼¼
    0.11
     supposed
    0.11
    Activations Density 0.341%

    No Known Activations