© 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. 10174
    Prev
    Next
    INDEX
    Explanations

    NMR assignments and measurements

    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
    umer
    -0.09
    bay
    -0.07
    moid
    -0.07
    åĨįçĶŁèĥ½æºIJ
    -0.07
     oe
    -0.07
    æĭĽåķĨ
    -0.07
    æĭĽ
    -0.07
     apel
    -0.07
    Ùħز
    -0.07
     Sioux
    -0.06
    POSITIVE LOGITS
    ursor
    0.07
    éĨį
    0.07
     unresolved
    0.07
     Windsor
    0.07
    lew
    0.07
     Orts
    0.07
    绾
    0.07
    lore
    0.07
    å·¥ä½ľç«Ļ
    0.07
    ortho
    0.06
    Activations Density 0.046%

    No Known Activations