© 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. 24013
    Prev
    Next
    INDEX
    Explanations

    greeting followed by "all" or "sweethearts"

    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
    æ¦
    -0.09
    æĭ¯
    -0.09
    https
    -0.08
    çĬĩ
    -0.08
    ä½Ĩæĺ¯ä»ĸ
    -0.08
     kiến
    -0.08
    åĵģä½į
    -0.08
    avian
    -0.08
    عÙĬ
    -0.08
    éo
    -0.08
    POSITIVE LOGITS
    ä»ĭç»įä¸Ģä¸ĭ
    0.09
    åIJĦä½į
    0.09
    ä»ij
    0.09
    大家ä¸Ģèµ·
    0.09
    读èĢħ
    0.09
    åħ¨ä½ĵ
    0.09
    大家åĪĨ享
    0.09
    nga
    0.09
    å°ıä¼Ļ伴们
    0.09
    大家
    0.08
    Activations Density 0.031%

    No Known Activations