© 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. 59233
    Prev
    Next
    INDEX
    Explanations

    Molly names and Allied Waste

    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
    ção
    -0.09
    Ùĥ
    -0.08
    oooooooo
    -0.08
     permanent
    -0.08
    bins
    -0.08
    cial
    -0.08
    oooo
    -0.08
    abil
    -0.08
    GREE
    -0.08
    çŁŃæŶéĹ´åĨħ
    -0.08
    POSITIVE LOGITS
    ness
    0.12
    ãģĹãģ¾ãģĨ
    0.11
    çĶ¨åĵģ
    0.10
    ucker
    0.09
    çĦ¶æĺ¯
    0.09
    odge
    0.09
    izer
    0.09
    об
    0.09
    ä¾į
    0.09
    ently
    0.08
    Activations Density 0.009%

    No Known Activations