© 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. 52353
    Prev
    Next
    INDEX
    Explanations

    built by / created by / written by

    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
    æŃ¢
    -0.09
    åģļ个
    -0.09
    è½®
    -0.09
    åľĪåŃIJ
    -0.09
    æĤ¼
    -0.09
    ä¼Ļ
    -0.09
    ä¸ĢåĪĩéĥ½
    -0.09
    åĩłåĪĨ
    -0.08
    æķ´ä¸ª
    -0.08
    ophile
    -0.08
    POSITIVE LOGITS
     someone
    0.11
    çĶ¨æīĭ
    0.10
    someone
    0.09
     people
    0.09
     Ñĩеловек
    0.09
    à¸Ħà¸Ļ
    0.09
    ç©¿è¿ĩ
    0.09
    人为
    0.09
    éĥĵ
    0.09
    ç©¿
    0.08
    Activations Density 0.086%

    No Known Activations