© 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. 28226
    Prev
    Next
    INDEX
    Explanations

    prank calls

    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
    -ok
    -0.08
    árom
    -0.08
     Sandro
    -0.08
     Biel
    -0.08
    endan
    -0.08
    èĥģ
    -0.08
    cience
    -0.07
    herits
    -0.07
    ä¹ĭæģ©
    -0.07
     Duy
    -0.07
    POSITIVE LOGITS
    æ¯ĵ
    0.07
    éĢIJæŃ¥
    0.07
    ical
    0.07
     chi
    0.07
    illions
    0.06
    neur
    0.06
    ÙĪار
    0.06
    illion
    0.06
    éĢIJ
    0.06
     seme
    0.06
    Activations Density 0.001%

    No Known Activations