© 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. 50596
    Prev
    Next
    INDEX
    Explanations

    URL fragments and identifiers

    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
    ä¸Ģ空
    -0.07
     champion
    -0.06
    à¹Į
    -0.06
    bet
    -0.06
    ä¸Ģ说
    -0.06
    ownload
    -0.06
    \:
    -0.06
    çļĦçĭĢæ³ģ
    -0.06
    çī¹å®ļ
    -0.06
    ×¢×ĵ
    -0.06
    POSITIVE LOGITS
    ieden
    0.08
     ÑģамоÑĥ
    0.08
    enske
    0.08
    uschen
    0.08
    unik
    0.07
     Quarti
    0.07
    kent
    0.07
    ilden
    0.07
    icao
    0.07
    -<?
    0.07
    Activations Density 0.149%

    No Known Activations