© 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. 19136
    Prev
    Next
    INDEX
    Explanations

    will attempt

    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
    å°ıä¼Ļä¼´
    -0.10
    oji
    -0.10
    สà¸ĩ
    -0.10
    пÑĥ
    -0.10
    å§Ĭ妹
    -0.09
    Éĵ
    -0.09
    åħ¶å®ĥ
    -0.09
    .radio
    -0.09
    人åĿĩ
    -0.09
    polator
    -0.09
    POSITIVE LOGITS
    女士
    0.10
    åħĪçĶŁ
    0.10
     Mr
    0.10
    ç»ĻæĤ¨
    0.09
    æĸ¹æīį
    0.09
    ãģĶãģĸãģĦãģ¾ãģĻ
    0.09
    请æĤ¨
    0.09
    è¿Ļè¾¹
    0.09
    ä¼ļå¼ķèµ·
    0.09
    æĬ±æŃī
    0.09
    Activations Density 0.036%

    No Known Activations