© 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. 7934
    Prev
    Next
    INDEX
    Explanations

    of course

    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
    æĥħ趣
    -0.09
    éĥľ
    -0.09
    èĦ±
    -0.09
    æľīæĦı
    -0.09
    åģļæ³ķ
    -0.09
    èĤĩ
    -0.08
    åħ¶å®ŀ
    -0.08
    rose
    -0.08
    æ¼¾
    -0.08
    .tp
    -0.08
    POSITIVE LOGITS
    å°ijä¸įäºĨ
    0.11
    ä¹Łæĺ¯ä¸Ģ个
    0.10
    æľīä¸Ģä½į
    0.10
    dden
    0.10
    .signature
    0.09
    éļ¾åħį
    0.09
    åĬłä¸Ĭ
    0.09
    æľīä¸Ģ
    0.09
    æľīä¸Ģ个
    0.09
     налиÑĩие
    0.08
    Activations Density 0.008%

    No Known Activations