© 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. 46034
    Prev
    Next
    INDEX
    Explanations

    data analytics and business intelligence

    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
     spacing
    -0.07
     cancellation
    -0.07
    éĵ¿
    -0.07
    advertisement
    -0.07
     vic
    -0.06
     reciprocal
    -0.06
    å¦Ĥéģĩ
    -0.06
    aro
    -0.06
    ä¿ĿæĬ¤å¥½
    -0.06
     иÑģпÑĭÑĤа
    -0.06
    POSITIVE LOGITS
    ä¸ŃçļĦæķ°æį®
    0.12
    çļĦæķ°æį®
    0.12
     data
    0.12
    (Data
    0.12
    ,data
    0.12
    æķ°æį®æĮĸæİĺ
    0.12
    æķ°æį®
    0.12
    )data
    0.12
    /data
    0.12
    æķ°æį®çļĦ
    0.11
    Activations Density 0.128%

    No Known Activations