© 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. 6204
    Prev
    Next
    INDEX
    Explanations

    experience and managing

    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
    aget
    -0.08
    åŀ«
    -0.08
    ASSES
    -0.08
    HAL
    -0.08
    ections
    -0.08
    -overlay
    -0.08
    çĤ¹åįĬ
    -0.08
    oshi
    -0.08
    zik
    -0.08
    æĨ©
    -0.07
    POSITIVE LOGITS
    èĩ³å°ij
    0.13
    æľĢå°ij
    0.13
    ä¸įå°ijäºİ
    0.11
    èµ·çłģ
    0.10
     ÑħоÑĤÑı
    0.10
    è¦ģä¹Ī
    0.10
     EITHER
    0.10
    èĤĥ
    0.09
    æĥ¬
    0.09
    æĹłè®ºå¦Ĥä½ķ
    0.09
    Activations Density 0.020%

    No Known Activations