© 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. 22115
    Prev
    Next
    INDEX
    Explanations

    case insensitive or ignore case

    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
    rium
    -0.08
    urst
    -0.08
    æĹłåIJį
    -0.08
    详ç»Ĩæııè¿°
    -0.08
    æĺĬ天
    -0.08
    estig
    -0.08
    ä¿±è¿Ľ
    -0.08
    ehu
    -0.08
    èĢĮè¿Ļ个
    -0.08
     Chois
    -0.08
    POSITIVE LOGITS
    åıªçľĭ
    0.08
    ä¸įèĢĥèĻij
    0.08
     ignores
    0.08
     ignoring
    0.08
     considers
    0.07
     Ignore
    0.07
     disreg
    0.07
     filtering
    0.07
     ignored
    0.07
    忽çķ¥
    0.07
    Activations Density 0.064%

    No Known Activations