© 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. 27508
    Prev
    Next
    INDEX
    Explanations

    explorers and historical expeditions

    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
    lair
    -0.08
    æ¼ĵæ±Ł
    -0.08
    èĥ½éĩı
    -0.07
    egasus
    -0.07
    (phase
    -0.07
    inati
    -0.07
    éĺµéĽ¨
    -0.06
    é¢IJåĴĮ
    -0.06
    ocrine
    -0.06
    ultas
    -0.06
    POSITIVE LOGITS
    æİ¢éĻ©
    0.12
    å¼Ģè¾Ł
    0.11
     frontier
    0.10
     explorer
    0.10
    å¼Ģæĭĵ
    0.09
     conquest
    0.09
     colonization
    0.09
    æ®ĸæ°ij
    0.09
     Frontier
    0.09
    è´¸æĺĵ
    0.09
    Activations Density 0.162%

    No Known Activations