© 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. 40151
    Prev
    Next
    INDEX
    Explanations

    neuropathic pain, spinal cord, plasticity

    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
    ä¼ĺ
    -0.10
    æĺ¾
    -0.09
    åĿŀ
    -0.09
    ç¾İ
    -0.09
    åıĪ被
    -0.08
    urre
    -0.08
     dol
    -0.08
    迷失
    -0.08
    åĩłçĤ¹
    -0.08
    失æݧ
    -0.08
    POSITIVE LOGITS
    çĸ¼
    0.10
    æģ
    0.09
    è¿Ń
    0.09
    ä¸ĬæĬ¥
    0.09
    çĸ¼çĹĽ
    0.09
     Intr
    0.09
    çĹĽ
    0.09
    æIJĤ
    0.09
    éĶĻ
    0.09
     Ranger
    0.09
    Activations Density 0.435%

    No Known Activations