© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42540
    Prev
    Next
    INDEX
    Explanations

    compared to, fiddle, vary, glad to see, puzzled, durable, oft, non-random, ost, ol

    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
    ifice
    -0.08
    icolore
    -0.07
    sembler
    -0.07
    iddle
    -0.07
    licer
    -0.07
    ..."
    -0.07
    nesday
    -0.07
    aternity
    -0.07
    istente
    -0.07
     коем
    -0.07
    POSITIVE LOGITS
    ä¸įåIJĮçļĦæĺ¯
    0.09
     inilah
    0.08
    ä¹Łç½¢
    0.08
    èĢĮè¨Ģä¹ĭ
    0.08
    yadi
    0.08
    è¨Ģéģĵ
    0.08
    ouch
    0.08
    çłĶ究表æĺİ
    0.08
    æĢ§æĺ¯
    0.08
    è°ļ
    0.08
    Activations Density 0.921%

    No Known Activations