© 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. 32207
    Prev
    Next
    INDEX
    Explanations

    spatial prepositions

    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
     Foley
    -0.09
    å¾Ĺ天
    -0.08
    æļĤç¼ĵ
    -0.08
    å½ĵæĪij
    -0.08
    é¦ĸ次
    -0.08
    leh
    -0.08
    ç¿°
    -0.08
     Meteor
    -0.08
    æ°Ķ象
    -0.08
    wyn
    -0.07
    POSITIVE LOGITS
    ä¸įå½±åĵį
    0.11
    èĮ¸
    0.10
    è¡Ģ液循çݯ
    0.10
    æ²¹èĦĤ
    0.10
    ä¼ļåIJĮ
    0.09
    æĹłéļľç¢į
    0.09
    çĭŃçªĦ
    0.09
    ä¸įæĸŃåľ°
    0.09
    建设åĴĮ
    0.09
    èįīåľ°
    0.09
    Activations Density 0.266%

    No Known Activations