© 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. 11535
    Prev
    Next
    INDEX
    Explanations

    preposition followed by article

    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
    ↵
    -0.07
     purported
    -0.07
    æĺ¯åħ¶
    -0.07
    2
    -0.07
    ä½Ĩæĺ¯çĶ±äºİ
    -0.06
    util
    -0.06
    åĪĻæĺ¯
    -0.06
     additionally
    -0.06
    n
    -0.06
     furthermore
    -0.06
    POSITIVE LOGITS
    -toggler
    0.10
    _stderr
    0.08
    æĿ¥å¾ĹåıĬ
    0.08
    çĮľä½łåĸľæ¬¢
    0.08
    REW
    0.08
    ç¾İå¾Ĺ
    0.08
    士æŀĹ
    0.08
    ÏģÏĨ
    0.08
    æīįæľīäºĨ
    0.08
    ersp
    0.08
    Activations Density 0.088%

    No Known Activations