© 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. 43176
    Prev
    Next
    INDEX
    Explanations

    next followed by time duration

    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
    åĽ½äº§
    -0.07
    ä¸Ģ次
    -0.07
    ä¸Ģç»ı
    -0.06
    èł»
    -0.06
     once
    -0.06
    ÏĪη
    -0.06
    point
    -0.06
    aras
    -0.06
    ara
    -0.06
    宿
    -0.06
    POSITIVE LOGITS
    igny
    0.08
    æĪijæĢķ
    0.08
    éĩijåĪ¸
    0.07
    ÑĢÑĤом
    0.07
    éĻ¢ç³»
    0.07
    -loader
    0.07
    çŃĶ主
    0.07
    atories
    0.07
    ork
    0.07
    çŃ¾å®ļ
    0.07
    Activations Density 0.003%

    No Known Activations