© 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. 46142
    Prev
    Next
    INDEX
    Explanations

    modal verbs: possibility and hypothetical

    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
     infatti
    -0.09
    ä¹ĭæīĢ以
    -0.08
    kses
    -0.07
     simply
    -0.07
    verture
    -0.07
    culares
    -0.07
     ÙģÙĤØ·
    -0.07
     zwar
    -0.07
     inoltre
    -0.07
    unesse
    -0.07
    POSITIVE LOGITS
     otherwise
    0.09
     altrimenti
    0.08
    çĶ±åħ¶
    0.08
    èµ·
    0.07
    istr
    0.07
    åľ°åĴĮ
    0.07
    çĶ±åİŁåijĬ
    0.07
     Otherwise
    0.07
    ä»ĭçŁ³
    0.07
    rigen
    0.07
    Activations Density 0.185%

    No Known Activations