© 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. 38797
    Prev
    Next
    INDEX
    Explanations

    temporalprepositions

    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
    è¿ĩåIJİ
    -0.09
    è¢Ĥ
    -0.09
     donc
    -0.09
     Hubb
    -0.09
    éĺ
    -0.08
    adora
    -0.08
    unas
    -0.08
    Mahon
    -0.08
    å¤ļåľ°
    -0.08
     Antar
    -0.08
    POSITIVE LOGITS
    åı°
    0.09
    åIJĦæł·
    0.09
    cock
    0.09
    åĿĬ
    0.09
    åIJĦå¼ıåIJĦæł·
    0.09
    èĭŁ
    0.08
    çļĦåIJĦ项
    0.08
    çļĦåIJĦç§į
    0.08
    æĹ¢
    0.08
    ockey
    0.08
    Activations Density 0.265%

    No Known Activations