© 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. 58837
    Prev
    Next
    INDEX
    Explanations

    numbers and types (II, 2, seven, A, B)

    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
    igi
    -0.08
    æĿı
    -0.07
    ardy
    -0.07
    myp
    -0.07
    è¦ģåħĪ
    -0.07
    ¿
    -0.07
    /pm
    -0.07
    arty
    -0.07
    æ´Ĺ
    -0.07
    åı¯ä»¥åħĪ
    -0.07
    POSITIVE LOGITS
    åĴĮéĩįçĤ¹
    0.08
    ç´§æİ¥çĿĢ
    0.08
    缮ãģĮ
    0.08
    顾åIJįæĢĿä¹ī
    0.07
    好礼
    0.07
    åıĪ称
    0.07
    enties
    0.07
    åĵŁ
    0.07
    é²²
    0.07
    opsis
    0.07
    Activations Density 0.031%

    No Known Activations