© 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. 14748
    Prev
    Next
    INDEX
    Explanations

    as comes before words like contracts, code, new, your

    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
    æѤæŶçļĦ
    -0.07
    sy
    -0.06
    atal
    -0.06
     auto
    -0.06
    çĶŁåŃĺ
    -0.06
     just
    -0.06
    ¤
    -0.05
    æĮģä¹ħçļĦ
    -0.05
    sa
    -0.05
     non
    -0.05
    POSITIVE LOGITS
    /if
    0.11
    éĥ¨å°±
    0.10
    ÙĨاÙĩ
    0.10
    á»ĥn
    0.09
    baugh
    0.09
    ÑħÑĤа
    0.09
    ynchronously
    0.09
    ynchronized
    0.08
    .tpl
    0.08
    ä½łæĬĬ
    0.08
    Activations Density 0.180%

    No Known Activations