© 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. 8336
    Prev
    Next
    INDEX
    Explanations

    directory commands

    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
    uera
    -0.07
    alcon
    -0.07
    ä¸ĭåIJĮ
    -0.07
    oyer
    -0.06
    ynch
    -0.06
    ritt
    -0.06
    lier
    -0.06
    好åĩłä¸ª
    -0.06
    å·ŀåĮº
    -0.06
    ä¹Łæľª
    -0.06
    POSITIVE LOGITS
    åIJĦç§įåIJĦæł·çļĦ
    0.09
    </think>
    0.09
     }:
    0.08
    orem
    0.08
    æĸ°åĬłåĿ¡
    0.08
    åıĪå¦Ĥ
    0.08
    ãĥ¯ãĤ¯ãĥģãĥ³
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    èĢ³çĨŁèĥ½è¯¦
    0.08
    俱ä¹IJéĥ¨
    0.08
    Activations Density 0.022%

    No Known Activations