© 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. 634
    Prev
    Next
    INDEX
    Explanations

    right

    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
    ity
    -0.13
    ä½Ĩä¸įéĻIJäºİ
    -0.11
    ITY
    -0.10
    ities
    -0.09
     Äijặn
    -0.09
    ÚĨÙĩ
    -0.08
    ount
    -0.08
    å¤ļãģĦ
    -0.08
    Ðķ
    -0.08
    åĻľ
    -0.08
    POSITIVE LOGITS
    o
    0.17
    a
    0.12
    ed
    0.12
    bamos
    0.12
    ا
    0.12
    о
    0.11
    缸è¾ħ缸æĪIJ
    0.10
    aft
    0.10
    ÑģÑĮ
    0.09
    ãģ¾ãģ¾
    0.09
    Activations Density 0.005%

    No Known Activations