© 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. 33859
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun or adjective

    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¥ģ
    -0.09
     infancy
    -0.08
    缸åħ³æĶ¿çŃĸ
    -0.08
    usu
    -0.08
    åľ¨çݩ家
    -0.08
    æķĻèĤ²éĥ¨
    -0.08
    åľĪåŃIJ
    -0.08
    ؤ
    -0.08
     haystack
    -0.08
    _HELP
    -0.08
    POSITIVE LOGITS
    æŃ£åĢ¼
    0.10
    åħ·æľīèī¯å¥½
    0.09
    符åIJĪæĿ¡ä»¶
    0.09
    å¹´è½»çļĦ
    0.09
    å¤Ħäºİ
    0.09
    åİ»è¿ĩ
    0.09
    顾
    0.09
    å¤Ħåľ¨
    0.09
    iques
    0.09
    个ä½ĵ
    0.09
    Activations Density 0.395%

    No Known Activations