© 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. 27604
    Prev
    Next
    INDEX
    Explanations

    unexpected results, lab report, introduction this

    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
    @if
    -0.07
    ä¸ĭåIJĮ
    -0.07
    çīĪæĿĥåĿĩ
    -0.07
    ³³³³³³³³
    -0.06
    (iOS
    -0.06
    æīĭæľºç«Ļ
    -0.06
    illow
    -0.06
    -eslint
    -0.06
    æĺ¯ä½ķåIJ«ä¹ī
    -0.06
    æŃ¦ä¾łä¿®çľŁ
    -0.06
    POSITIVE LOGITS
    ihu
    0.09
    Å¡el
    0.08
    缸åħ³éĹ®é¢ĺ
    0.08
    åĪĨæŀIJåıĬ
    0.07
    grund
    0.07
     Lastly
    0.07
    omer
    0.07
    å±ħçĦ¶æĺ¯
    0.07
    Related
    0.07
     related
    0.07
    Activations Density 0.001%

    No Known Activations