© 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. 40139
    Prev
    Next
    INDEX
    Explanations

    regeneration and repair

    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
     ÑįкÑģп
    -0.09
    ãģĭãĤĭ
    -0.09
    æºī
    -0.09
    apy
    -0.08
    robe
    -0.08
    æŨ
    -0.08
    æ·ŀ
    -0.08
    ÇIJ
    -0.08
     surre
    -0.08
    éļĺ
    -0.08
    POSITIVE LOGITS
    ively
    0.11
    ivo
    0.10
    umin
    0.09
    翳
    0.09
    iele
    0.09
    ving
    0.09
    igung
    0.09
    ists
    0.09
    /rec
    0.09
    -minded
    0.09
    Activations Density 0.026%

    No Known Activations