© 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. 34442
    Prev
    Next
    INDEX
    Explanations

    math and variable suffixes

    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
     identifiable
    -0.08
    ãĤĤãģ£ãģ¨
    -0.08
     íĬ¹íŀĪ
    -0.07
    olim
    -0.07
    नà¥įन
    -0.07
    apas
    -0.07
    ัà¸Ķ
    -0.07
    abut
    -0.07
    èĢĮä¸Ķæĺ¯
    -0.07
    à¹Ĥà¸Ķยà¹Ģà¸īà¸ŀาะ
    -0.07
    POSITIVE LOGITS
    并æĮīçħ§
    0.10
    åIJĮæŶå°Ĩ
    0.10
    并å°Ĩ
    0.10
    çĦ¶åIJİçĶ¨
    0.09
    çĦ¶åIJİ
    0.09
     rá»ĵi
    0.09
     resulting
    0.09
    并æĮī
    0.09
    并使çĶ¨
    0.09
    çĦ¶åIJİåĨį
    0.09
    Activations Density 0.062%

    No Known Activations