© 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. 50259
    Prev
    Next
    INDEX
    Explanations

    proper nouns and abbreviations

    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
    åİ»åĵªéĩĮ
    -0.10
    ä¸Ĭä¸ĸ纪
    -0.09
    æĶ¹éĿ©å¼ĢæĶ¾
    -0.08
    ued
    -0.08
    åİ»åĵªåĦ¿
    -0.08
    immer
    -0.08
    orts
    -0.08
    arty
    -0.08
    icho
    -0.08
     WWII
    -0.08
    POSITIVE LOGITS
    æľĢè¿ij
    0.11
    ä»İåݻ年
    0.09
    蹶
    0.09
    åľ¨ä»Ĭå¹´
    0.09
    缮åīįæŃ£åľ¨
    0.09
    è¿ijåĩłå¹´
    0.09
     lately
    0.09
    ÑĩаÑĤ
    0.08
    MAL
    0.08
    æĤ²åĵĢ
    0.08
    Activations Density 0.263%

    No Known Activations