© 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. 22840
    Prev
    Next
    INDEX
    Explanations

    documentation tags and code snippets

    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
    ity
    -0.07
    æĿ¥å¾ĹåıĬ
    -0.06
    ehler
    -0.06
    'av
    -0.06
    èݱåĿŀ
    -0.06
    cks
    -0.06
     amb
    -0.06
     Awal
    -0.06
    |array
    -0.06
    Õ¡Õ¾
    -0.06
    POSITIVE LOGITS
    åĩºåİ»
    0.08
    æŁIJæŁIJ
    0.07
    биÑĤ
    0.07
    æĽ¿å°¼
    0.07
    adge
    0.07
    åĩºåİ»çļĦ
    0.07
    advertisement
    0.07
    egram
    0.07
    /lgpl
    0.07
    åIJ«éĩij
    0.07
    Activations Density 0.053%

    No Known Activations