© 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. 40769
    Prev
    Next
    INDEX
    Explanations

    mathematical variable assignment

    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
    åŀ
    -0.07
     Mér
    -0.07
     mer
    -0.07
    ienes
    -0.07
    请çĻ»å½ķ
    -0.07
    mer
    -0.07
    ½
    -0.07
    æľĿå»·
    -0.07
    åįķä½įåıĤåĬł
    -0.07
     Merk
    -0.06
    POSITIVE LOGITS
    hofer
    0.08
    大åĪ©
    0.07
    onale
    0.07
    خاÙĦ
    0.07
    /parser
    0.07
    ONUS
    0.06
    erland
    0.06
    eron
    0.06
    onal
    0.06
     versus
    0.06
    Activations Density 0.067%

    No Known Activations