© 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. 29285
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in -ally, -ly

    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
     ÐŁÐ¾Ð¿ÑĢо
    -0.09
    urator
    -0.08
    ervised
    -0.08
    меÑĢа
    -0.08
     ÐĴÑģÑĤÑĢе
    -0.08
     Istitu
    -0.08
     juridi
    -0.08
    skom
    -0.08
    teggi
    -0.07
     Сооб
    -0.07
    POSITIVE LOGITS
    ally
    0.10
    ently
    0.09
    arily
    0.09
    fully
    0.09
    èĢĮè¨Ģ
    0.09
    çĦ¶
    0.09
    ously
    0.08
    ically
    0.08
    antly
    0.08
    ately
    0.08
    Activations Density 2.511%

    No Known Activations