© 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. 32076
    Prev
    Next
    INDEX
    Explanations

    conditional clauses, consequence clauses

    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
    请èģĶç³»
    -0.09
    âĺľ
    -0.09
    æĪij们è¦ģ
    -0.09
    asma
    -0.09
    обÑĢ
    -0.08
    поÑĩ
    -0.08
    æĽ´è¦ģ
    -0.08
    clc
    -0.08
    ExceptionHandler
    -0.08
    пÑĥÑĤ
    -0.08
    POSITIVE LOGITS
    æľīè¶³å¤ŁçļĦ
    0.11
    ä¸Ģå®ļçļĦ
    0.11
    åľ¨è¿ĩåİ»
    0.10
    ãģĭãģ¤
    0.09
    åĵī
    0.09
    é¡ĺæĦı
    0.09
    åľ¨åIJĮä¸Ģ
    0.09
    åĪĩæĪIJ
    0.09
     haven
    0.09
    缺å°ij
    0.09
    Activations Density 0.113%

    No Known Activations