© 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. 26664
    Prev
    Next
    INDEX
    Explanations

    conjunctions and auxiliary verbs

    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
     <<-
    -0.09
    ascript
    -0.08
    _defined
    -0.08
    主次
    -0.08
     whats
    -0.07
    åĪ©æĸ¯
    -0.07
    hattan
    -0.07
     restitu
    -0.07
    ĩ´
    -0.07
    полни
    -0.07
    POSITIVE LOGITS
     neither
    0.07
    群
    0.07
     otherwise
    0.06
    éĨĴ
    0.06
    oc
    0.06
    ä¸įçĦ¶
    0.06
    ä½Ĩå®ĥ们
    0.06
     بÙĬد
    0.06
    ...
    0.06
    y
    0.06
    Activations Density 0.060%

    No Known Activations