© 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. 58430
    Prev
    Next
    INDEX
    Explanations

    evil overlord, villains, and enemies

    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
    оÑĩки
    -0.08
    chal
    -0.08
    æ¼¾
    -0.07
    arie
    -0.07
    quires
    -0.07
    æľ¬æĸĩçĶ±
    -0.07
     forz
    -0.07
    çĭ¸
    -0.07
     поÑĤÑĢа
    -0.07
     mirac
    -0.07
    POSITIVE LOGITS
     hại
    0.09
    รà¹īาย
    0.08
    icious
    0.08
    arial
    0.08
    fully
    0.08
    åĽ¢ä¼Ļ
    0.07
    ous
    0.07
    /host
    0.07
    -leaning
    0.07
     lurking
    0.07
    Activations Density 0.287%

    No Known Activations