© 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. 7034
    Prev
    Next
    INDEX
    Explanations

    charged molecules and size

    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
     magn
    -0.07
    ä¾
    -0.07
    åIJĮæŃ¥
    -0.06
     infinit
    -0.06
    lage
    -0.06
    åĪ°ä½į
    -0.06
    agal
    -0.06
     synchron
    -0.06
    leps
    -0.06
    ัà¸Ļà¸Ĺ
    -0.06
    POSITIVE LOGITS
    æľīè¾ĥ强çļĦ
    0.09
     bulky
    0.09
    åħ·æľīè¾ĥ强çļĦ
    0.08
    èµĦ产çļĦ
    0.08
     mobility
    0.08
    çĽIJåĴĮ
    0.08
    é²ľæĺİçļĦ
    0.08
    çµĦãģ¿
    0.07
    çĭ¬è¡Į
    0.07
    强çĥĪçļĦ
    0.07
    Activations Density 0.024%

    No Known Activations