© 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. 33746
    Prev
    Next
    INDEX
    Explanations

    elapsed time periods

    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
     ninete
    -0.08
    祸é¦ĸ
    -0.08
    μαÏĦο
    -0.07
    俱ä¹IJéĥ¨
    -0.07
    ŃĶ
    -0.07
    éĻ¤æѤ
    -0.07
    åĮĸåıijå±ķ
    -0.07
    Ĵáŀ
    -0.07
    æ¯ıç§Ĵ
    -0.07
    ÑģÑĥди
    -0.07
    POSITIVE LOGITS
     weeks
    0.08
     days
    0.08
     years
    0.08
     months
    0.08
    \xa
    0.07
     time
    0.07
     (!
    0.07
    _days
    0.07
    åŁł
    0.07
    æľ½
    0.06
    Activations Density 0.277%

    No Known Activations