© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34030
    Prev
    Next
    INDEX
    Explanations

    Redistribution, Stephanie, agon, trav

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¨åŁŁ
    -0.09
    æµij身
    -0.08
    缤
    -0.08
    äºĭåħĪ
    -0.08
     volunt
    -0.08
    IDO
    -0.08
    å¼Łå¼Ł
    -0.08
    æĥ§
    -0.07
    ä¸Ĭä¸ĭ游
    -0.07
    éķ¿éķ¿çļĦ
    -0.07
    POSITIVE LOGITS
    å¿Ĺ强
    0.11
    ä½ĵèĤ²é¦Ĩ
    0.10
    ç²ij
    0.10
    天æīį
    0.09
    åĬ±å¿Ĺ
    0.08
    ALE
    0.08
    æķĻèĤ²éĥ¨
    0.08
     resign
    0.08
    絾
    0.08
     Rib
    0.08
    Activations Density 0.052%

    No Known Activations