© 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. 63466
    Prev
    Next
    INDEX
    Explanations

    determiner + noun

    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
    åºĶ该æľī
    -0.08
    angelo
    -0.07
    AWN
    -0.07
    åĪĨ享åĨħ容
    -0.07
    åºĶ该
    -0.07
    abo
    -0.07
    sembler
    -0.07
    æĪIJåħ¨
    -0.07
    ooks
    -0.07
    thon
    -0.07
    POSITIVE LOGITS
    çĶ±æѤ
    0.08
     thereby
    0.08
    è¿Ļä¹Ł
    0.08
    ä¹ŁåĽłæѤ
    0.08
     zatem
    0.08
    oret
    0.07
    å¦ĤæѤä¸ĢæĿ¥
    0.07
     thus
    0.07
    erma
    0.07
     بذÙĦÙĥ
    0.07
    Activations Density 0.038%

    No Known Activations