© 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. 60955
    Prev
    Next
    INDEX
    Explanations

    usually/typically followed by prepositions

    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
    çħ¦
    -0.12
    éģ½
    -0.10
    çĵ¤
    -0.10
    人æŃ»äº¡
    -0.10
    æĩĤäºĭ
    -0.10
    ç³ĸå°¿
    -0.09
    çļĦ人éĥ½
    -0.09
    è¿Ļ群
    -0.09
    åĬŀäºĭ
    -0.09
    æķ°çłģ
    -0.09
    POSITIVE LOGITS
     ones
    0.10
    UCH
    0.09
    éĽĨä¸Ńåľ¨
    0.09
     preferably
    0.09
    åľ°çĤ¹
    0.09
    åĩºèĩª
    0.09
     mine
    0.08
    åĩºäºİ
    0.08
    oodles
    0.08
    eya
    0.08
    Activations Density 0.097%

    No Known Activations