© 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. 41822
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific terms

    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
    pector
    -0.08
    alang
    -0.07
    该åĮº
    -0.07
    ontology
    -0.07
    pected
    -0.07
    cke
    -0.07
    该楼å±Ĥ
    -0.07
    ç¦ģæŃ¢è½¬è½½
    -0.07
    loth
    -0.06
    å¾ģéĽĨ
    -0.06
    POSITIVE LOGITS
    itten
    0.07
    instein
    0.07
     Roose
    0.07
    æĵĩ
    0.07
    åľ
    0.07
    IRE
    0.07
    _strlen
    0.07
    .xyz
    0.07
    åĬĿ说
    0.07
     Grade
    0.07
    Activations Density 0.002%

    No Known Activations