© 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. 3564
    Prev
    Next
    INDEX
    Explanations

    suffixes like 'ed', 'ate', 'ing'

    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
    ÑģÑı
    -0.13
    ़
    -0.10
    à§įত
    -0.10
    à§įস
    -0.10
    //*
    -0.10
    à±į
    -0.10
    ëį°ìļĶ
    -0.09
    etts
    -0.09
    вÑĢопей
    -0.09
    à¥įह
    -0.09
    POSITIVE LOGITS
    åľ¨
    0.09
    s
    0.08
    аем
    0.08
    çĦ¶å¤§
    0.08
    itude
    0.08
    ãģ¾ãģ¾
    0.08
     viá»ĩc
    0.08
    oring
    0.07
     Ristor
    0.07
    åľ¨åħ·ä½ĵ
    0.07
    Activations Density 0.872%

    No Known Activations