© 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. 60576
    Prev
    Next
    INDEX
    Explanations

    involvement in or role of

    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
    çĪµ
    -0.10
    .qual
    -0.09
    è¿ĺæĺ¯ä¼ļ
    -0.09
    WSTR
    -0.09
    çľĭä»ĸ
    -0.09
    æĶĺ
    -0.09
    .Lo
    -0.09
    سÙĬر
    -0.09
    饷
    -0.09
     пÑĢоÑĤиво
    -0.09
    POSITIVE LOGITS
    åħ±éĿĴ
    0.09
    åĨ·æ°´
    0.09
    pd
    0.09
    åľ¨åĨħçļĦ
    0.08
    ror
    0.08
    éĥ¨ä¸»ä»»
    0.08
    achen
    0.08
    çĸij
    0.08
    ayan
    0.08
    åľ¨äºİ
    0.08
    Activations Density 0.112%

    No Known Activations