© 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. 5781
    Prev
    Next
    INDEX
    Explanations

    other biological complicated executive curved

    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
    çĦī
    -0.09
    ãĤ¹ãĤ¿ãĥ¼
    -0.09
    cem
    -0.09
    åı¸
    -0.09
    ãģĹãģŁãĤĤãģ®
    -0.08
    ongs
    -0.08
    éĤij
    -0.08
    åĿĢ
    -0.08
    umi
    -0.08
    çĶļèĩ³è¿ĺ
    -0.08
    POSITIVE LOGITS
    èĮµ
    0.09
    æ¯ıä¸Ģ次
    0.09
    å¿ĥ缮
    0.08
     chore
    0.08
    湫
    0.08
    çĽĪ
    0.08
    å·§å¦Ļ
    0.08
     betray
    0.08
    å¤ļéĩį
    0.08
    æ¡«
    0.08
    Activations Density 0.187%

    No Known Activations