© 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. 16773
    Prev
    Next
    INDEX
    Explanations

    -ing endings, -orous, -omatic suffixes

    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
    /remove
    -0.10
    ement
    -0.09
    inkel
    -0.09
    DebugEnabled
    -0.09
    lectual
    -0.09
    boss
    -0.09
    eds
    -0.09
    祺
    -0.08
    istrar
    -0.08
    å°±æĺ¯ä¸Ģ个
    -0.08
    POSITIVE LOGITS
    aal
    0.09
    oted
    0.09
    rary
    0.09
    getState
    0.09
    aar
    0.08
    INO
    0.08
    éĢ¼è¿ij
    0.08
     ÑģÑĥммÑĥ
    0.08
    çĶ¨é¤IJ
    0.08
    arus
    0.08
    Activations Density 0.751%

    No Known Activations