© 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. 59068
    Prev
    Next
    INDEX
    Explanations

    android dimension attributes

    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
    Negative Logits
    人æĹł
    -0.07
    ément
    -0.07
    æ´¥
    -0.07
    ques
    -0.06
    ä¸İä½ľçĶ¨
    -0.06
    رÙĪØ©
    -0.06
    æ³ī
    -0.06
    اظ
    -0.06
     plat
    -0.06
    æī¶
    -0.06
    POSITIVE LOGITS
    åľĪ
    0.08
    uvi
    0.08
    jem
    0.07
     khao
    0.07
    accio
    0.07
    ekk
    0.07
    -counter
    0.07
     Ñĥви
    0.07
    steen
    0.07
    .logging
    0.07
    Activations Density 0.022%

    No Known Activations