© 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. 17676
    Prev
    Next
    INDEX
    Explanations

    section starts {#sec1-

    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
    ewa
    -0.08
    annen
    -0.06
    ining
    -0.06
     Aix
    -0.06
    åİ¥
    -0.06
    æ²IJ
    -0.06
    perfect
    -0.06
    交åºķ
    -0.06
    ocen
    -0.06
    åĺĺ
    -0.06
    POSITIVE LOGITS
    adini
    0.07
    åĬŀäºĭæĮĩåįĹ
    0.07
    енÑĤ
    0.06
    ä¸İæĿİ
    0.06
    вилÑģÑı
    0.06
    ä¸ĭæĶ¾
    0.06
    å¤ĩ
    0.06
    SetTitle
    0.06
    cade
    0.06
     Lead
    0.06
    Activations Density 0.010%

    No Known Activations