© 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. 15788
    Prev
    Next
    INDEX
    Explanations

    PATH, speed, activity, location

    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
     reconciliation
    -0.07
    elaar
    -0.07
    宽容
    -0.06
    éĨ
    -0.06
    æ´Ĺ礼
    -0.06
    è´¢
    -0.06
     Loot
    -0.06
     parchment
    -0.06
     LY
    -0.06
    éĴ±åĮħ
    -0.06
    POSITIVE LOGITS
     locom
    0.11
    è¿IJåĬĽ
    0.11
    ervo
    0.10
     speeds
    0.10
    æĺ¯ä¸ĢæĶ¯
    0.09
    æŶéĢŁ
    0.09
    speed
    0.09
    -speed
    0.09
     velocities
    0.09
     Speed
    0.09
    Activations Density 0.856%

    No Known Activations