© 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. 47211
    Prev
    Next
    INDEX
    Explanations

    suitably/appropriately/properly/well modifying nouns

    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
    Äģtu
    -0.08
    ahu
    -0.07
    заÑĢ
    -0.07
    æ³ŀ
    -0.07
    é¢ĺ为
    -0.07
    æŃ£åľ¨
    -0.07
    ãĥ¼ãĥĪãĥ«
    -0.07
    grama
    -0.07
    koz
    -0.07
    åİĨåı²æĢ§
    -0.07
    POSITIVE LOGITS
    «
    0.07
    acca
    0.07
    纪åħĥ
    0.07
    æ¤Ĵ
    0.07
     numbers
    0.07
    io
    0.06
    yak
    0.06
    ia
    0.06
    åIJĦæĸ¹
    0.06
    iazza
    0.06
    Activations Density 0.018%

    No Known Activations