© 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. 6173
    Prev
    Next
    INDEX
    Explanations

    plant roots and berries

    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
    Creature
    -0.11
    éľī
    -0.10
    rians
    -0.10
    åĬ¨çī©åĽŃ
    -0.10
    设æĸ½å»ºè®¾
    -0.09
    æ¸Ķæ°ij
    -0.09
    åİ©
    -0.09
    è²ĺ
    -0.09
     lÆ°á»Ľi
    -0.09
     Creature
    -0.09
    POSITIVE LOGITS
    èįī
    0.14
     обÑĭ
    0.10
     popular
    0.09
     ordinary
    0.09
     grass
    0.09
     Grass
    0.09
    éļıå¤Ħåı¯è§ģ
    0.09
    å±ŀ
    0.08
    æĬ½åĩº
    0.08
    æ¡ij
    0.08
    Activations Density 0.133%

    No Known Activations