© 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. 57490
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers, Roman numerals, year numbers

    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
    è£Ĥ
    -0.07
    ½
    -0.07
    POSE
    -0.07
    rial
    -0.07
    ÑģÑĤей
    -0.07
     Pue
    -0.07
    artal
    -0.07
    å½ĵæŶ
    -0.06
    åľ¨å®¶éĩĮ
    -0.06
    åįģæĿ¡
    -0.06
    POSITIVE LOGITS
    bern
    0.08
    ophone
    0.07
     occasion
    0.07
    交éģĵ
    0.07
    letter
    0.07
    æľĭ
    0.07
    ä¸ŃåĽ½äººçļĦ
    0.07
    .RunWith
    0.07
    rt
    0.06
    èī³éĺ³
    0.06
    Activations Density 0.221%

    No Known Activations