© 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. 23148
    Prev
    Next
    INDEX
    Explanations

    math and technical phrasing

    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
    Porno
    -0.12
    ölker
    -0.10
    æľ¬æ¥¼
    -0.09
    é»Ħ页
    -0.09
    ãĥĵãĤ¸
    -0.09
    åĬłåħ¥ä¹¦æŀ¶
    -0.09
    intree
    -0.09
    æľĢæĸ°æĸĩç«ł
    -0.09
    ideographic
    -0.09
    ä¸ĢèģĬ
    -0.09
    POSITIVE LOGITS
     Mathematic
    0.07
    L
    0.07
    D
    0.06
    æѤ
    0.06
     convention
    0.06
    P
    0.06
    ©
    0.06
    p
    0.06
     algebra
    0.06
    S
    0.06
    Activations Density 0.409%

    No Known Activations