© 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. 15513
    Prev
    Next
    INDEX
    Explanations

    transit and transportation

    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
    çĹħç¨ĭ
    -0.07
     Realty
    -0.06
     Beauty
    -0.06
    çĹħæĪ¿
    -0.06
    OfYear
    -0.06
    åľ¨çĶŁäº§
    -0.06
    onn
    -0.06
     bedside
    -0.06
     nors
    -0.06
     decorators
    -0.06
    POSITIVE LOGITS
    éĢļåĭ¤
    0.11
    åĩºè¡ĮçļĦ
    0.11
    åħ¬åħ±äº¤éĢļ
    0.10
    åĩºè¡Į
    0.10
    æľĪ票
    0.10
    æį¢ä¹ĺ
    0.10
     transportation
    0.09
    æĭ¥åłµ
    0.09
    客è¿IJ
    0.09
     commuting
    0.09
    Activations Density 0.128%

    No Known Activations