© 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. 32543
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    olf
    -0.07
    worthy
    -0.06
    haus
    -0.06
    зо
    -0.06
    ewise
    -0.06
    æĶ¯
    -0.06
     воÑģ
    -0.06
    akra
    -0.06
    kos
    -0.06
    éģĵè¿ľ
    -0.06
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.07
    áŀ·áŀı
    0.07
    erja
    0.07
    æĺ¯ä¸Ģå¹´
    0.07
    jenje
    0.07
    asilan
    0.07
    anda
    0.07
    IfExists
    0.07
    iere
    0.07
     Thrones
    0.07
    Activations Density 0.088%

    No Known Activations