© 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. 7122
    Prev
    Next
    INDEX
    Explanations

    no any

    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
    IVEN
    -0.08
    rach
    -0.07
    å¥½ä¸ľè¥¿
    -0.07
     полÑĮзованиÑı
    -0.07
    agan
    -0.07
    atera
    -0.07
    é«Ķ質
    -0.07
    æ¸ħæ°Ķ
    -0.07
    èĩªèº«å»ºè®¾
    -0.07
    ideo
    -0.07
    POSITIVE LOGITS
    æĹłä»»ä½ķ
    0.10
    æĹłéľĢ
    0.09
    å¿ħè¦ģ
    0.09
     никакиÑħ
    0.08
     aucune
    0.08
     nothing
    0.08
    åĪ«æĹł
    0.08
    æĹł
    0.08
    并æĹł
    0.08
    ä¹Łæ²¡æľīä»Ģä¹Ī
    0.08
    Activations Density 0.242%

    No Known Activations