© 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. 31340
    Prev
    Next
    INDEX
    Explanations

    longer, higher, scale

    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
    aed
    -0.08
    away
    -0.08
    -away
    -0.07
    ادÙĬ
    -0.07
    å°ıåѦè¯Ńæĸĩ
    -0.07
     Buc
    -0.07
     felic
    -0.07
     buc
    -0.07
     ë¿IJë§Į
    -0.07
    å°ijåħĪ
    -0.07
    POSITIVE LOGITS
    è¿Ļ个æķ°åŃĹ
    0.12
    å®ŀéĻħ
    0.09
    æĽ´é«ĺ
    0.09
     nearer
    0.09
     longer
    0.09
    æĽ´éķ¿
    0.09
     closer
    0.08
    è¿Ļåıªæĺ¯
    0.08
     higher
    0.08
     actual
    0.08
    Activations Density 0.257%

    No Known Activations