© 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. 12578
    Prev
    Next
    INDEX
    Explanations

    contrast media

    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
    宾
    -0.07
    驼
    -0.07
     handful
    -0.07
     tez
    -0.07
    Entry
    -0.07
    itol
    -0.06
    entry
    -0.06
    ÑĦаÑĢ
    -0.06
    à¸ĺร
    -0.06
     plentiful
    -0.06
    POSITIVE LOGITS
    CTOR
    0.07
    agne
    0.07
    认è¯ĨåĪ°äºĨ
    0.06
    ierÃł
    0.06
    imiz
    0.06
    ayah
    0.06
    å¥ķ
    0.06
    æ¯Ķè¾ĥ好çļĦ
    0.06
    adow
    0.06
    åĨīåĨī
    0.06
    Activations Density 0.004%

    No Known Activations