© 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. 26699
    Prev
    Next
    INDEX
    Explanations

    each followed by a verb

    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
    æĹ¶è¾°
    -0.10
    éĩĮéĿ¢çļĦ
    -0.10
    寺éĻ¢
    -0.09
    æīĭä¸ŃçļĦ
    -0.09
    åĨį说
    -0.09
    åįĪåIJİ
    -0.09
    ä¹ĭæīĢ
    -0.09
    çĥŃæIJľ
    -0.09
    è¿Ļæīį
    -0.09
    æĦģ
    -0.09
    POSITIVE LOGITS
    åIJĦæľī
    0.10
    aris
    0.09
    è¿Ī
    0.09
     cler
    0.08
    åĪĬ
    0.08
    eur
    0.08
    åĮħåĮħ
    0.08
    ãĢħ
    0.08
    åIJĦèĩª
    0.08
    æľīä¸ĢäºĽ
    0.08
    Activations Density 0.036%

    No Known Activations