© 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. 37294
    Prev
    Next
    INDEX
    Explanations

    km or miles

    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
    clar
    -0.09
    å¿ĺäºĨ
    -0.09
    ifer
    -0.08
    bug
    -0.08
    æĥ³åİ»
    -0.08
    ä¹ĭå¤ľ
    -0.08
     compet
    -0.08
    åĺĪ
    -0.08
    목
    -0.08
    ksen
    -0.08
    POSITIVE LOGITS
    åįķ车
    0.11
    éĺ²çº¿
    0.11
    åł¤
    0.10
    线æĿ¡
    0.10
     coastline
    0.10
    æĭ¬
    0.09
     dÃłi
    0.09
    å®Įå¤ĩ
    0.09
    å®ĮåĸĦçļĦ
    0.09
     ribbon
    0.09
    Activations Density 0.030%

    No Known Activations