© 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. 17990
    Prev
    Next
    INDEX
    Explanations

    adrenoceptors

    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
    ugt
    -0.07
    éĥİ
    -0.07
    gtest
    -0.07
    धि
    -0.06
    å¤ļãģı
    -0.06
    lak
    -0.06
    天å¤ĸ
    -0.06
    illo
    -0.06
    commended
    -0.06
    nian
    -0.06
    POSITIVE LOGITS
    åĪĨè£Ĥ
    0.14
    åĪĨ为
    0.14
     splits
    0.14
    åĪĨæĪIJ
    0.14
    主è¦ģåĪĨ为
    0.14
     divided
    0.14
     Split
    0.13
    åĪĨçĤº
    0.13
     splitted
    0.13
    split
    0.13
    Activations Density 0.379%

    No Known Activations