© 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. 61258
    Prev
    Next
    INDEX
    Explanations

    negation and lack of specification

    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
    umul
    -0.09
    orda
    -0.08
    .Encode
    -0.07
    éĽĨä¸Ńç²¾åĬĽ
    -0.07
    åĪ°åĮ»éĻ¢
    -0.07
    ä¸įè§ģäºĨ
    -0.07
    .logs
    -0.06
    americano
    -0.06
    ady
    -0.06
    ä»ħä»£è¡¨ä½ľèĢħ
    -0.06
    POSITIVE LOGITS
     explicit
    0.09
    æĺİç¡®
    0.08
     explicitly
    0.08
    æĺİç¡®è¦ģæ±Ĥ
    0.08
    ç«ĭæĸ°
    0.08
    æĺİç¡®çļĦ
    0.08
     Explicit
    0.08
    Explicit
    0.07
     expressly
    0.07
     mention
    0.07
    Activations Density 0.002%

    No Known Activations