© 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. 20227
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas with "where"

    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
     {}:
    -0.07
    ucin
    -0.07
    )="
    -0.07
    éĥ½åıªæĺ¯
    -0.07
    )":
    -0.07
    ÙĦÙĬÙģ
    -0.07
    enk
    -0.07
    ibbon
    -0.07
    jim
    -0.07
    icer
    -0.07
    POSITIVE LOGITS
     wobei
    0.07
    æĺĤ
    0.07
    waan
    0.07
     ???
    0.06
    çIJħ
    0.06
     suss
    0.06
     Äijiá»ĥn
    0.06
    ãģ³
    0.06
     toe
    0.06
    .Check
    0.06
    Activations Density 0.006%

    No Known Activations