© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37770
    Prev
    Next
    INDEX
    Explanations

    know if/what/where/why

    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
    å¼ĢéĺĶ
    -0.09
    Paginator
    -0.09
    åľ¨ä¸Ģèµ·
    -0.09
    å¯ĩ
    -0.09
    æijŃ
    -0.09
    åı£å¤´
    -0.08
    èĨı
    -0.08
    urrenc
    -0.08
    ãģĵãģĵãģ¾ãģ§
    -0.08
    Ûŀ
    -0.08
    POSITIVE LOGITS
    çŁ¥éģĵ
    0.10
    å¾ĹçŁ¥
    0.09
    æĽ´å¤ļçļĦ
    0.09
     about
    0.09
    æĽ´å¤ļä¿¡æģ¯
    0.08
    es
    0.08
    æĥ³çŁ¥éģĵ
    0.08
    Ans
    0.08
    羣缸
    0.08
    å®ŀå®ŀåľ¨åľ¨
    0.08
    Activations Density 0.029%

    No Known Activations