© 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. 26033
    Prev
    Next
    INDEX
    Explanations

    people involved

    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
    kah
    -0.10
    主æĦı
    -0.10
    æ¯ĵ
    -0.10
    æµĴ
    -0.09
    åıĮæĸ¹
    -0.09
    两级
    -0.09
    说å®ŀ
    -0.08
    使èĢħ
    -0.08
    ation
    -0.08
    ishment
    -0.08
    POSITIVE LOGITS
    åŁŃ
    0.08
    ä¸įä»ħè¦ģ
    0.08
    饱满
    0.08
    å§ĭç»Īä¿ĿæĮģ
    0.08
     Mim
    0.08
    aged
    0.08
    avid
    0.08
    vang
    0.08
    èĮ
    0.08
    çī¹åĪ«å£°æĺİ
    0.08
    Activations Density 0.024%

    No Known Activations