© 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. 62116
    Prev
    Next
    INDEX
    Explanations

    use to explain purpose or application

    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
    ssize
    -0.07
    ovin
    -0.07
    å¤ĩå¿ĺ
    -0.06
    opia
    -0.06
     اÙĦÙħÙĦا
    -0.06
    gree
    -0.06
    éħ¿
    -0.06
    ambang
    -0.06
    ighth
    -0.06
    è¿Ļç§įäºĭ
    -0.06
    POSITIVE LOGITS
    åľ°ä½¿çĶ¨
    0.09
     полÑĥÑĩеннÑĭÑħ
    0.09
    æīĭä¸ŃçļĦ
    0.08
     полÑĥÑĩен
    0.08
    è¿Ļæł¹
    0.08
     misuse
    0.08
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļà¹Į
    0.08
     полÑĥÑĩеннÑĭе
    0.08
    urpose
    0.07
    æīĭéĩĮçļĦ
    0.07
    Activations Density 0.675%

    No Known Activations