© 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. 21304
    Prev
    Next
    INDEX
    Explanations

    accompanied or accompanying file

    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
    аÑĢÑĮ
    -0.10
    éªĸ
    -0.09
    aub
    -0.09
    inium
    -0.09
    cape
    -0.09
    ifying
    -0.09
    太快
    -0.09
    ified
    -0.09
    ä¸ĢåŃĹ
    -0.09
    igr
    -0.08
    POSITIVE LOGITS
    ry
    0.11
    ä¼´éļı
    0.11
    æĪijåİ»
    0.10
     acompaña
    0.10
    大家ä¸Ģèµ·
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.09
     accompanies
    0.09
     acompanh
    0.09
     accompany
    0.09
    æĭĪ
    0.09
    Activations Density 0.025%

    No Known Activations