© 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. 22410
    Prev
    Next
    INDEX
    Explanations

    an/a followed by a noun

    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
    串
    -0.11
    afort
    -0.10
    æĹłæĦı
    -0.10
    å¤įæ´»
    -0.09
    éķ¶åµĮ
    -0.09
     Hus
    -0.09
    èĢģ家
    -0.09
    ÙĦÙĪÙħ
    -0.09
    çł»
    -0.09
    åĮį
    -0.09
    POSITIVE LOGITS
    们çļĦ
    0.12
    们
    0.12
    åĢij
    0.11
    群ä½ĵ
    0.10
    çıŃåŃIJ
    0.10
    ä¸ĢæĶ¯
    0.09
    åĽ¢éĺŁ
    0.09
    ilt
    0.09
    ä¸Ģ群
    0.09
    棱
    0.09
    Activations Density 0.095%

    No Known Activations