© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29548
    Prev
    Next
    INDEX
    Explanations

    use/utilize/usage

    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
    Negative Logits
    ä»»
    -0.09
    LAG
    -0.09
     кли
    -0.09
    ä¸Ģæīĭ
    -0.09
    edList
    -0.09
     Garland
    -0.08
    dia
    -0.08
    âĸ¹
    -0.08
    iles
    -0.08
     اÙĦÙħسؤÙĪÙĦ
    -0.08
    POSITIVE LOGITS
    ç§ijæĬĢæĪIJæŀľ
    0.10
    ä¼ļè§īå¾Ĺ
    0.09
     planet
    0.08
    饴
    0.08
    éģĵè·¯ä¸Ĭ
    0.08
    éĶĢåĶ®æ¸łéģĵ
    0.08
    ä¸ŃåįĪ
    0.08
    è¿Ļéĥ¨
    0.08
    ç¨İåĬ¡å±Ģ
    0.08
    èĥ¯
    0.08
    Activations Density 0.091%

    No Known Activations