© 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. 925
    Prev
    Next
    INDEX
    Explanations

    specific details or statements

    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
     Fortune
    -0.10
    ä¸įåĪ°
    -0.10
    æīįæľī
    -0.09
    çļĦéĢļçŁ¥
    -0.09
    workspace
    -0.09
    çķª
    -0.09
    çıij
    -0.09
    éĻĽ
    -0.09
    ä¸įä»ħè¦ģ
    -0.09
    orb
    -0.08
    POSITIVE LOGITS
    åħ·ä½ĵ
    0.12
    ä½ķæŶ
    0.12
    åħ·ä½ĵçļĦ
    0.10
    æĺ¯è°ģ
    0.10
    ä»Ģä¹ĪæŶåĢĻ
    0.10
     конкÑĢеÑĤ
    0.10
    สาà¸Ĥา
    0.09
    ä½ķ
    0.09
    cheon
    0.08
    æľīä½ķ
    0.08
    Activations Density 0.027%

    No Known Activations