© 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. 44912
    Prev
    Next
    INDEX
    Explanations

    Romanian prince

    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
    )?.
    -0.08
    åĨħ容æıIJä¾Ľæĸ¹
    -0.07
    èĢĮå½ĵ
    -0.07
     sogenannte
    -0.07
    )__
    -0.07
    "$
    -0.07
    è¯Ŀ
    -0.07
    xil
    -0.07
    aum
    -0.07
    Cpp
    -0.07
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.10
    æĿ¥åķ¦
    0.08
     Same
    0.07
     SAME
    0.07
    ÑĤÑģÑı
    0.07
    strand
    0.06
     Nein
    0.06
    usable
    0.06
    .jpg
    0.06
    acad
    0.06
    Activations Density 0.010%

    No Known Activations