© 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. 23449
    Prev
    Next
    INDEX
    Explanations

    learn more about

    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
    æĽ´å¤ļ
    -0.12
     more
    -0.11
    æĽ´å¤ļçļĦæĺ¯
    -0.10
    éļ¶å±ŀ
    -0.10
    æĽ´å¤ļçļĦ
    -0.10
    æĽ´å¤ļ精彩
    -0.09
    ead
    -0.09
    åıĪä¸Ģ次
    -0.09
    æĽ´å¤ļä¿¡æģ¯
    -0.09
     MORE
    -0.09
    POSITIVE LOGITS
    ç»ĨèĬĤ
    0.10
    ç£ĭ
    0.09
    ëĭ´
    0.09
    çģ¾åĮº
    0.09
    éĢŀ
    0.08
     about
    0.08
    _details
    0.08
     Mour
    0.08
     details
    0.08
    çĶ³è¯ī
    0.08
    Activations Density 0.039%

    No Known Activations