© 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. 60634
    Prev
    Next
    INDEX
    Explanations

    excess of other things

    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
    ä¸Ģæĥ³
    -0.08
     ulang
    -0.08
    اÛĮÛĮ
    -0.08
    itz
    -0.08
    iany
    -0.08
    è¶ĬæĿ¥è¶Ĭè¿ij
    -0.08
    趣
    -0.08
    ifications
    -0.07
    -esque
    -0.07
    夫æĸ¯åŁº
    -0.07
    POSITIVE LOGITS
    es
    0.10
    iveness
    0.09
    ively
    0.08
    åĴĮä¸į足
    0.08
    ives
    0.07
    å¤ļçļĦ
    0.07
    alous
    0.07
     thereof
    0.07
    s
    0.07
    ened
    0.06
    Activations Density 0.009%

    No Known Activations