© 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. 38709
    Prev
    Next
    INDEX
    Explanations

    exception is made

    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
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    ument
    -0.07
     Sax
    -0.07
    缴æİ¥æĪĸ
    -0.07
    สูà¸ķร
    -0.07
     airborne
    -0.06
    æī¬
    -0.06
    åIJ«ç¬ij
    -0.06
     “âĢ¦
    -0.06
    çļĦä¸Ģ
    -0.06
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.08
    临åħ¶
    0.07
    åĶı
    0.07
    èī²åĪĹ
    0.07
     Oops
    0.07
    urop
    0.07
    æĹłæīĢè°ĵ
    0.07
    åģļçļĦæĺ¯
    0.07
    illos
    0.07
    à¹ģห
    0.07
    Activations Density 0.004%

    No Known Activations