© 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. 16734
    Prev
    Next
    INDEX
    Explanations

    tomato and tomato paste

    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
    ness
    -0.12
    è´¢
    -0.10
    umin
    -0.09
    é«Ń
    -0.08
    itt
    -0.08
    ष
    -0.08
    wald
    -0.08
    urement
    -0.08
    éĻĮçĶŁäºº
    -0.08
    appa
    -0.08
    POSITIVE LOGITS
    croft
    0.09
    arez
    0.09
     ÑĦакÑĤ
    0.09
    iators
    0.09
    lette
    0.08
    ä¸Ģç¬Ķ
    0.08
    è¾Ļ
    0.08
    Skills
    0.08
     Heights
    0.08
    ially
    0.08
    Activations Density 0.005%

    No Known Activations