© 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. 25281
    Prev
    Next
    INDEX
    Explanations

    watch or witness

    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
    iox
    -0.07
     found
    -0.06
     lái
    -0.06
     touch
    -0.06
     personal
    -0.06
    abyrinth
    -0.06
    çļĦæ°Ķæģ¯
    -0.06
    ousing
    -0.06
     chÃŃ
    -0.06
    æĻ®æŁ¥
    -0.06
    POSITIVE LOGITS
     наблÑİдаÑĤÑĮ
    0.10
     ì§Ģì¼ľ
    0.10
     beobachten
    0.09
     dõi
    0.09
    缮çĿ¹
    0.09
    è§Ĥå¯ŁåĪ°
    0.09
    ãĤĴ観
    0.09
     watched
    0.09
     watching
    0.09
    äºĭæĢģ
    0.09
    Activations Density 0.211%

    No Known Activations