© 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. 21513
    Prev
    Next
    INDEX
    Explanations

    time duration and length

    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
    天åīį
    -0.08
    èĩªå·±çļĦ人
    -0.08
    Matchers
    -0.08
    ä¸ĩæĪ·
    -0.08
     sensit
    -0.08
    values
    -0.07
     millions
    -0.07
    emper
    -0.07
    XObject
    -0.07
    çĻ¾åĢį
    -0.07
    POSITIVE LOGITS
    æŶéķ¿
    0.12
     longer
    0.12
     length
    0.12
     lenght
    0.12
     duration
    0.11
    -length
    0.11
    length
    0.11
    duration
    0.10
     longest
    0.10
    -long
    0.10
    Activations Density 0.242%

    No Known Activations