© 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. 19247
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
    çĽ¸ä¼¼æĸĩçĮ®
    -0.09
    _constants
    -0.09
    imana
    -0.08
    stö
    -0.08
    æĢİä¹ĪåĬŀåij¢
    -0.08
    types
    -0.08
     petró
    -0.08
    atorie
    -0.08
     подле
    -0.08
    atori
    -0.08
    POSITIVE LOGITS
    æĮĩ
    0.10
    æĮĩçļĦæĺ¯
    0.09
     refers
    0.08
    æĮĩæŃ£
    0.08
    æĺ¯æĮĩ
    0.07
     referring
    0.07
    å°±æĺ¯æĮĩ
    0.07
     implies
    0.07
    æŁIJ人
    0.07
    æĮĩçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations