© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48349
    Prev
    Next
    INDEX
    Explanations

    relationship between

    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
    管æīĢ
    -0.08
    PathParam
    -0.07
    ä¸İä»ĸ人
    -0.07
    otr
    -0.07
    éĴĪ对æĢ§
    -0.07
    è¿ŀåIJĮ
    -0.07
    对çħ§
    -0.07
    对åºĶçļĦ
    -0.07
    å°Ĩä¸İ
    -0.07
     contrast
    -0.07
    POSITIVE LOGITS
     بÙĬÙĨÙĩÙħا
    0.14
     mutual
    0.13
    å½¼æѤ
    0.13
    两èĢħ
    0.12
    äºĴ为
    0.12
    äºĮèĢħ
    0.12
    å½¼æѤçļĦ
    0.12
     keduanya
    0.12
    mut
    0.11
    åIJĦèĩª
    0.11
    Activations Density 0.053%

    No Known Activations