© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2221
    Prev
    Next
    INDEX
    Explanations

    duration

    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
    å½ĵåľº
    -0.08
    屡次
    -0.07
    屡屡
    -0.07
    åħį费注åĨĮ
    -0.07
    ða
    -0.07
    æĹ©å¹´
    -0.06
    ÏĢοιη
    -0.06
    æĸ°çĶ¨æĪ·
    -0.06
    两年åīį
    -0.06
    redi
    -0.06
    POSITIVE LOGITS
     duration
    0.25
     durations
    0.23
     Duration
    0.22
    duration
    0.22
    Duration
    0.22
    æľŁéĹ´
    0.21
     lasted
    0.21
     durée
    0.21
    _duration
    0.20
    æľŁéĹ´çļĦ
    0.20
    Activations Density 0.626%

    No Known Activations