© 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. 9213
    Prev
    Next
    INDEX
    Explanations

    is/are followed by adjectives

    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
    çĶļèĩ³æĺ¯
    -0.10
    æģķ
    -0.09
    çĶļèĩ³
    -0.09
     <![
    -0.09
    åĩ¡æĺ¯
    -0.09
    çļĦ家åºŃ
    -0.08
    为åĩĨ
    -0.08
    æ¯Ķå¦Ĥ
    -0.08
     donc
    -0.08
    odus
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·æīįèĥ½
    0.13
    éĤ£æł·
    0.11
    å®ŀåľ¨å¤ª
    0.10
    ppo
    0.10
    碰
    0.09
    éĤ£æł·çļĦ
    0.09
    çı£
    0.09
    å¤Ħåľ¨
    0.09
    éĤ£ä¸ªæŶåĢĻ
    0.09
    ä¸Ĭå¹´åIJĮæľŁ
    0.09
    Activations Density 0.088%

    No Known Activations