© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55277
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with multiplication

    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
    Õ¶Õ¥ÖĢ
    -0.07
    triz
    -0.07
    giv
    -0.07
    ниÑĨа
    -0.07
    ä¿¡æģ¯çĶ±
    -0.06
    å°ĨéĤ£
    -0.06
    ÙĬاء
    -0.06
    /access
    -0.06
    家ãģ¯
    -0.06
    大亨
    -0.06
    POSITIVE LOGITS
    ãĢģãĢĮ
    0.09
    ·
    0.08
    ãĥ»
    0.08
    åĦ¿çļĦ
    0.07
    ãĢģ
    0.07
    ä¹ĭæīĢ
    0.07
    ·
    0.07
    ï½¥
    0.07
    elage
    0.07
    odont
    0.07
    Activations Density 0.022%

    No Known Activations