© 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. 48111
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by determiners

    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
     ведÑĮ
    -0.09
    åŁĭ
    -0.09
    esty
    -0.09
    ãi
    -0.08
    rade
    -0.08
    ä¼¼ä¹İæĺ¯
    -0.08
    бан
    -0.08
    Primitive
    -0.08
    åĩ¤åĩ°
    -0.08
    å¥ij
    -0.08
    POSITIVE LOGITS
    ris
    0.10
    åĨĴçĿĢ
    0.08
    ä»Ģä¹Īäºĭ
    0.08
    ä»Ģä¹ĪåİŁåĽł
    0.08
    off
    0.08
    MMC
    0.08
    æ´ĭæ´ĭ
    0.08
    ĵåIJį
    0.08
    è¿Ļç¯ĩæĸĩç«ł
    0.08
    ento
    0.08
    Activations Density 0.111%

    No Known Activations