© 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. 48685
    Prev
    Next
    INDEX
    Explanations

    mediumalternating currentwavesfringescrest trough

    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
    ilogy
    -0.07
    برÛĮ
    -0.07
    /framework
    -0.07
    iggins
    -0.07
     spotlight
    -0.06
    ilog
    -0.06
     lengthy
    -0.06
    è°ĭ
    -0.06
     notoriously
    -0.06
    è¬Ģ
    -0.06
    POSITIVE LOGITS
    äº¤æĽ¿
    0.10
     alternating
    0.08
    å½¢æĪIJçļĦ
    0.08
     sinus
    0.08
     crest
    0.08
    è°·
    0.07
    æ³¢çļĦ
    0.07
    èµ·ä¼ı
    0.07
     trough
    0.07
    waves
    0.07
    Activations Density 0.009%

    No Known Activations