© 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. 29592
    Prev
    Next
    INDEX
    Explanations

    modified, modification, modify

    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
     McM
    -0.10
    é«ĺç´łè´¨
    -0.09
    ery
    -0.08
    à¸Ĭา
    -0.08
    å¹ķ
    -0.08
    osaic
    -0.08
    主æīĵ
    -0.08
    gon
    -0.08
    è°¨
    -0.08
    çĦ¯
    -0.08
    POSITIVE LOGITS
    æĶ¹éĢł
    0.18
    æĶ¹è£ħ
    0.17
     Modifications
    0.15
     modifications
    0.15
     modification
    0.14
    æĶ¹èī¯
    0.14
    ä¿®æĶ¹
    0.14
     Modification
    0.13
    modification
    0.13
    .modify
    0.13
    Activations Density 0.153%

    No Known Activations