© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20848
    Prev
    Next
    INDEX
    Explanations

    license and copyright information

    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
    ogui
    -0.10
    صة
    -0.08
    itas
    -0.08
    éĶļ
    -0.08
    adol
    -0.08
     صØŃ
    -0.08
    éĥ´å·ŀ
    -0.08
    æ´¾éģ£
    -0.08
    毫æĹłçĸij
    -0.08
    éŨæĪ·
    -0.08
    POSITIVE LOGITS
    arez
    0.10
    åı¯æł¹æį®
    0.09
    ç»ĵæĿŁäºĨ
    0.08
    PAR
    0.08
    è¾ĵäºĨ
    0.08
    ä¸įå¿į
    0.08
    _MODULE
    0.08
    è¦ģ好好
    0.08
    nect
    0.08
    è¦ģä¸įçĦ¶
    0.08
    Activations Density 0.232%

    No Known Activations