© 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. 1664
    Prev
    Next
    INDEX
    Explanations

    negation or qualification

    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
    èĻ½çĦ¶æĺ¯
    -0.13
    èĻ½çĦ¶åľ¨
    -0.13
    èĻ½çĦ¶ä»ĸ
    -0.12
    èĻ½çĦ¶
    -0.11
     zwar
    -0.11
    èĻ½æĺ¯
    -0.10
     although
    -0.10
    èĻ½å°ı
    -0.10
    èĻ½çĦ¶æĪij们
    -0.10
    éĽĸçĦ¶
    -0.10
    POSITIVE LOGITS
    boh
    0.07
    ulti
    0.07
    å¤Ł
    0.07
    èĢħä¹Ł
    0.07
    K
    0.06
    ç»Ŀ对ä¸įæĺ¯
    0.06
     rá»ĩt
    0.06
    rick
    0.06
    ç§ij夫
    0.06
    eson
    0.06
    Activations Density 0.158%

    No Known Activations