© 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. 24744
    Prev
    Next
    INDEX
    Explanations

    toll free help number

    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
    à¸Ńà¸Ńà¸Ļ
    -0.07
    reicher
    -0.07
    åIJĪåIJĮæŶ
    -0.07
    usercontent
    -0.07
    欢è¿İæĤ¨çļĦ
    -0.07
    éķ¿è¶³
    -0.07
    éĺħ读æĿĥéĻIJ
    -0.07
    ä¿Ŀä½ı
    -0.07
    æĹ¥çĶµ
    -0.07
    kert
    -0.07
    POSITIVE LOGITS
     toll
    0.10
     hotline
    0.09
    æĭ¨æīĵ
    0.08
     unarmed
    0.08
     hel
    0.08
     кÑĢÑĥглоÑģÑĥ
    0.08
     Piso
    0.08
     nationwide
    0.07
    ä¸ĢéĶ®
    0.07
    æľįåĬ¡çĥŃ线
    0.07
    Activations Density 0.053%

    No Known Activations