© 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. 52223
    Prev
    Next
    INDEX
    Explanations

    home automation and networks

    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
    adj
    -0.08
     Fate
    -0.08
    éŃĤ
    -0.08
     bi
    -0.08
    æĶ¹éĿ©å¼ĢæĶ¾
    -0.07
    ais
    -0.07
     delegate
    -0.07
    飵
    -0.07
    èĢĥå¯Ł
    -0.07
    æ´Ĺæīĭ
    -0.07
    POSITIVE LOGITS
    ç³»ç»Ł
    0.11
     Seam
    0.11
     ÑģиÑģÑĤема
    0.10
    _SB
    0.10
    dap
    0.10
    system
    0.10
     system
    0.10
     ÙĨظاÙħ
    0.09
    系統
    0.09
    æĹłç¼Ŀ
    0.09
    Activations Density 0.050%

    No Known Activations