© 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. 9234
    Prev
    Next
    INDEX
    Explanations

    date and text sequences

    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
     ÑģоÑħÑĢани
    -0.07
     cob
    -0.07
     Ying
    -0.07
    éĢļåijĬ
    -0.07
     Ber
    -0.07
    ãĥģãĥ£ãĥ³
    -0.07
    Bru
    -0.07
    æĪĸèĢħ说
    -0.07
    åĢı
    -0.07
    partials
    -0.07
    POSITIVE LOGITS
    以åıĬåħ¶ä»ĸ
    0.11
    ç®Ģ称
    0.10
    .ke
    0.10
    å¾Ĺ天
    0.09
    ä¸ĭ称
    0.09
    社ä¼ļåĮĸ
    0.09
    [$_
    0.09
    è¿Ļ个åIJįåŃĹ
    0.09
     bang
    0.09
    uet
    0.09
    Activations Density 0.965%

    No Known Activations