© 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. 56018
    Prev
    Next
    INDEX
    Explanations

    wished you, master the, every animal, the Lion, when first, step through, just west, stood in

    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
     aforementioned
    -0.08
     («
    -0.08
    åīįè¿°
    -0.08
    æľīæѤ
    -0.07
    æѤç§į
    -0.07
    æ¶īäºĭ
    -0.07
    次è¦ģ
    -0.07
    ana
    -0.07
    ä¸įåĮħåIJ«
    -0.07
    ited
    -0.07
    POSITIVE LOGITS
     countless
    0.08
    æľĢæĢķ
    0.08
     bustling
    0.08
    bres
    0.07
    tene
    0.07
     intricate
    0.07
    ä»Ĭ天å°ıç¼ĸ
    0.07
    æĪ¸
    0.07
    urul
    0.07
    ront
    0.07
    Activations Density 0.077%

    No Known Activations