© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48375
    Prev
    Next
    INDEX
    Explanations

    preposition followed by "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ĺ
    -0.11
    HING
    -0.09
     curs
    -0.08
    Mp
    -0.08
    æĵİ
    -0.08
    Click
    -0.08
    _dropout
    -0.08
     Click
    -0.08
     whistle
    -0.08
     Ñĩеловека
    -0.07
    POSITIVE LOGITS
    ¢åįķ
    0.11
    åIJĮæĥħ
    0.10
    ä»»ä½ķä¸Ģ个
    0.10
    å¼Ģ头
    0.10
    趣åij³
    0.10
    åĩºçİ°åľ¨
    0.10
    ç»ļ丽
    0.10
    骸
    0.10
    便ä¼ļ
    0.09
    é²ľèī³
    0.09
    Activations Density 0.060%

    No Known Activations