© 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. 55826
    Prev
    Next
    INDEX
    Explanations

    when followed by a noun or gerund

    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
    å¥
    -0.09
    ussian
    -0.09
    éªı
    -0.09
    oner
    -0.08
    UCE
    -0.08
    åıĸæļĸ
    -0.08
    ä½Ĩä»į
    -0.08
     dec
    -0.08
    ucc
    -0.08
    åĮºåŁŁæĢ§
    -0.08
    POSITIVE LOGITS
    ä½ķæŶ
    0.11
    ä»Ģä¹ĪæŶåĢĻ
    0.11
    ä¸Ĭ次
    0.09
    è´¦åı·
    0.09
    soever
    0.09
    ä¸ĵä¸ļ人士
    0.09
    æĹ¥ä¸ĬåįĪ
    0.09
    ÙĬا
    0.08
    åݻ年
    0.08
    ä»ĬåIJİ
    0.08
    Activations Density 0.053%

    No Known Activations