© 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. 9900
    Prev
    Next
    INDEX
    Explanations

    possessive nouns and verbs

    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
    aglio
    -0.07
    ä¸ĢæŦåĩºçİ°
    -0.07
    onge
    -0.07
     Bong
    -0.07
    agul
    -0.07
    éĴµ
    -0.07
    ç±»
    -0.07
     voc
    -0.07
    engel
    -0.07
    å½ĵ头
    -0.06
    POSITIVE LOGITS
    пÑĮ
    0.07
    ارات
    0.07
     زÙĬد
    0.07
    å¾Īé«ĺåħ´
    0.07
    ystone
    0.07
    æĺ¨å¤©æĻļä¸Ĭ
    0.07
    çļĪ
    0.07
    ntag
    0.06
    æĺ¨å¤©
    0.06
     ||=
    0.06
    Activations Density 0.084%

    No Known Activations