© 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. 48560
    Prev
    Next
    INDEX
    Explanations

    accommodations, pregnancy, Factory, Servlet, winner

    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
    çѱ
    -0.06
    ÙĨÙģ
    -0.06
    byname
    -0.06
    西è¡Ĺ
    -0.06
     Bedien
    -0.06
    æł¡åĽŃéĩĮ
    -0.06
    สึà¸ģ
    -0.06
    instr
    -0.06
    -input
    -0.06
    sehen
    -0.06
    POSITIVE LOGITS
    äºĮèĥİ
    0.07
    åĩºæłı
    0.07
    ucin
    0.07
    好è¿IJ
    0.07
    Coder
    0.07
    umpt
    0.07
    erci
    0.07
    xen
    0.07
    åįĥéĩij
    0.07
    oping
    0.07
    Activations Density 1.055%

    No Known Activations