© 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. 6086
    Prev
    Next
    INDEX
    Explanations

    Winston Churchill Kissinger

    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
    OfWeek
    -0.10
    _NPC
    -0.09
    еÑģ
    -0.09
    æķ´æ´ģ
    -0.09
    åħ¨æĹ¥åĪ¶
    -0.09
    åŃIJéĩĮ
    -0.09
    avig
    -0.08
    æķ´é½IJ
    -0.08
    lessly
    -0.08
    ored
    -0.08
    POSITIVE LOGITS
    amat
    0.12
    cow
    0.10
    ÙĬات
    0.09
    iams
    0.09
    IfNeeded
    0.09
    hip
    0.09
    owie
    0.08
    пÑĢав
    0.08
    èļĵ
    0.08
    imed
    0.08
    Activations Density 0.004%

    No Known Activations