© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57105
    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
    uide
    -0.08
    itten
    -0.08
    åį´æ²¡
    -0.07
    à¦ľà¦¨
    -0.07
    ır
    -0.07
    åį´ä¸į
    -0.07
    æŃ»æ´»
    -0.07
     peu
    -0.07
    车身
    -0.07
    为è¾ħ
    -0.07
    POSITIVE LOGITS
     perfect
    0.09
     necessarily
    0.08
    åĩŃ空
    0.08
     ÑĥнивеÑĢ
    0.08
    sole
    0.08
    ä¸ĢæĪIJ
    0.08
    åħ¨èĥ½
    0.07
     outright
    0.07
    åįģåħ¨
    0.07
    åħ¨èĩªåĬ¨
    0.07
    Activations Density 0.030%

    No Known Activations