© 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. 48630
    Prev
    Next
    INDEX
    Explanations

    prime factors, remainder, first

    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
    åĬłåħ³æ³¨
    -0.09
    ington
    -0.08
    rish
    -0.08
    à¸Ńาย
    -0.07
    cak
    -0.07
    红楼
    -0.07
    ayne
    -0.07
    ä¸įå°½
    -0.07
    ذب
    -0.07
    asal
    -0.07
    POSITIVE LOGITS
    umbles
    0.07
    -Methods
    0.07
    ç¥ŀåħµ
    0.07
    çıĬçıĬ
    0.07
    Typed
    0.06
    è¾ĵåĩºçļĦ
    0.06
    æıIJ交çļĦ
    0.06
    ÙĤاد
    0.06
    å«
    0.06
     mog
    0.06
    Activations Density 0.001%

    No Known Activations