© 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. 51450
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, and common abbreviations

    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
    ÑĦелÑĮ
    -0.08
    æīĵå¥½åŁºç¡Ģ
    -0.08
    venes
    -0.08
    .subplot
    -0.07
    OWER
    -0.07
    alon
    -0.07
    çļĦåĪ¶ä½ľæĸ¹æ³ķ
    -0.07
    icen
    -0.07
    æĥķ
    -0.07
     Aspe
    -0.07
    POSITIVE LOGITS
     ultr
    0.07
    ems
    0.07
    اث
    0.06
    emis
    0.06
    ering
    0.06
     sem
    0.06
    人头
    0.06
    ifferences
    0.06
    aunch
    0.06
    æĹ¥çĶ¨
    0.06
    Activations Density 0.001%

    No Known Activations