© 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. 20467
    Prev
    Next
    INDEX
    Explanations

    Names of people and 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
     [âĢ¦]
    -0.09
     [âĢ¦
    -0.08
     (âĢ¦)
    -0.07
    [âĢ¦]
    -0.07
     (...)
    -0.07
     Âł
    -0.07
    âĢ¦”
    -0.07
     âĢ¦
    -0.07
    ³³³³
    -0.06
    èij
    -0.06
    POSITIVE LOGITS
    建åįİ
    0.09
    å¿Ĺ强
    0.09
    jit
    0.08
    æħ·
    0.08
     Alegre
    0.08
    ä¸Ģåıij
    0.08
    .Sin
    0.08
    审
    0.08
    ¬ģ
    0.07
     Klos
    0.07
    Activations Density 0.001%

    No Known Activations