© 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. 35045
    Prev
    Next
    INDEX
    Explanations

    prime numbers and calculations

    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
    usher
    -0.08
    phinx
    -0.08
    çĴ¨
    -0.08
     closely
    -0.07
    èĬ±çµ®
    -0.07
    åı¯ä»¥æľīæķĪåľ°
    -0.07
    vette
    -0.07
    å¹´ä¾Ĩ
    -0.07
    AGAIN
    -0.07
     pensi
    -0.07
    POSITIVE LOGITS
     ordinal
    0.08
     calcul
    0.07
    ETHER
    0.07
    åij¨åħ¬
    0.07
    æŶåħī
    0.06
    ðŁĺ
    0.06
    Calculator
    0.06
     unreal
    0.06
    ç½ijåıĭ
    0.06
    calcul
    0.06
    Activations Density 0.270%

    No Known Activations