© 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. 30744
    Prev
    Next
    INDEX
    Explanations

    forces and their effects

    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
    NU
    -0.07
     esque
    -0.06
    ä¸įæĪIJ
    -0.06
    æŀļ举
    -0.06
    iere
    -0.06
    è¡Į为è§ĦèĮĥ
    -0.06
    æĪIJç«ł
    -0.06
    érique
    -0.06
    åħ¨éĿ¢å®ĮæĪIJ
    -0.06
    ériques
    -0.06
    POSITIVE LOGITS
    平衡
    0.09
    ãng
    0.08
     balancing
    0.08
    ä¸ŃåĴĮ
    0.08
    ernes
    0.07
    éĥ½æĺ¯çĶ±
    0.07
    itta
    0.07
    æĶ¯ä»ĺç»Ļ
    0.07
     Eins
    0.07
    åºĶä»ĺ
    0.07
    Activations Density 0.006%

    No Known Activations