© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9064
    Prev
    Next
    INDEX
    Explanations

    words related to 'order' or 'associated'

    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
    нÑĸм
    -0.08
    ##_
    -0.08
    URRE
    -0.08
     diak
    -0.07
    engg
    -0.07
    ignons
    -0.07
    ίÏĥ
    -0.07
    زد
    -0.07
    pk
    -0.07
    ignon
    -0.07
    POSITIVE LOGITS
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.08
    allo
    0.07
    und
    0.07
    Ale
    0.07
    èĮī
    0.07
    alie
    0.06
    ÙĪسÙĬ
    0.06
    åĪĨä¼ļ
    0.06
     pur
    0.06
    unan
    0.06
    Activations Density 0.011%

    No Known Activations