© 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. 21973
    Prev
    Next
    INDEX
    Explanations

    here placeholder

    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
    endale
    -0.07
    ç»Ŀä¸ĸ
    -0.07
    ä¸įæĶ¶
    -0.07
    iales
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    ustom
    -0.07
    ForKey
    -0.07
    infeld
    -0.07
    uding
    -0.06
    shall
    -0.06
    POSITIVE LOGITS
    qu
    0.07
    here
    0.07
     ÙĩÙĨا
    0.07
    å¤įåĪ¶æĪĸ
    0.07
    个人æĪĸ
    0.07
    заÑĢ
    0.07
    iá»ģm
    0.07
    ozilla
    0.07
    itia
    0.07
     here
    0.06
    Activations Density 0.001%

    No Known Activations