© 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. 9642
    Prev
    Next
    INDEX
    Explanations

    negation

    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
    è¯ĿæĿ¥
    -0.08
    à¸ĩวà¸Ķ
    -0.08
    ä¸įåĨį
    -0.08
    ä¹ĭä¸į
    -0.08
    ÑĤÑĥа
    -0.08
    otify
    -0.08
    å°±ä¸įåĨį
    -0.08
    lider
    -0.08
    uality
    -0.07
    èĻ½çĦ¶ä¸įæĺ¯
    -0.07
    POSITIVE LOGITS
    ï¼Į
    0.07
    rn
    0.07
    enz
    0.06
    ë
    0.06
    enia
    0.06
     obstante
    0.06
    rna
    0.06
    enic
    0.06
     because
    0.06
    ,
    0.06
    Activations Density 0.003%

    No Known Activations