© 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. 23435
    Prev
    Next
    INDEX
    Explanations

    temporal connectors

    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
    침
    -0.09
    çľĭåľ¨
    -0.08
    সà§įয
    -0.07
    eck
    -0.07
    eben
    -0.07
    顽强çļĦ
    -0.07
     prie
    -0.07
    ÏĢι
    -0.07
    riz
    -0.07
    essin
    -0.07
    POSITIVE LOGITS
     when
    0.13
     khi
    0.11
    å½ĵä¸Ģ个
    0.11
     lorsqu
    0.10
    å½ĵæĪij们
    0.10
    when
    0.10
     quando
    0.10
     cuando
    0.09
    å½ĵåħ¶
    0.09
     عÙĨدÙħا
    0.09
    Activations Density 0.464%

    No Known Activations