© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23579
    Prev
    Next
    INDEX
    Explanations

    Political parties and organizations

    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
    stored
    -0.07
    çıį
    -0.07
    åİĨæĿ¥
    -0.07
     accumulated
    -0.07
     stored
    -0.07
    øv
    -0.06
    å¾Īæ¸ħæ¥ļ
    -0.06
    ä¸Ī
    -0.06
     Forbes
    -0.06
     cached
    -0.06
    POSITIVE LOGITS
    çŃīæĸ°
    0.11
    åºĶè¿IJèĢĮçĶŁ
    0.10
    çŃīä¸Ģæī¹
    0.10
    åIJİæĿ¥åıĪ
    0.09
    éĽıå½¢
    0.09
    é¦ĸ家
    0.09
     soon
    0.09
    çļĦ建ç«ĭ
    0.09
    æľĢåĪĿçļĦ
    0.09
    åIJİæĿ¥çļĦ
    0.09
    Activations Density 0.419%

    No Known Activations