© 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. 14584
    Prev
    Next
    INDEX
    Explanations

    not followed by negated state

    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
     não
    -0.11
    ä¹ĭä¸į
    -0.11
    ä¸įè°ĥ
    -0.10
    Ùħاء
    -0.10
    infeld
    -0.09
    não
    -0.09
    zelfde
    -0.09
    lots
    -0.09
    ино
    -0.09
    ÙĦات
    -0.08
    POSITIVE LOGITS
     necessarily
    0.10
    oriously
    0.09
    éĤ£ä¹Ī容æĺĵ
    0.08
     yet
    0.08
     a
    0.08
     an
    0.08
    ä¸ĢåĽŀäºĭ
    0.07
    ,
    0.07
    /w
    0.07
     necesariamente
    0.07
    Activations Density 0.117%

    No Known Activations