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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20634
    Prev
    Next
    INDEX
    Explanations

    on-site residents

    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
    ç²Ĺç³Ļ
    -0.09
    æĹħè¡Į社
    -0.08
    çªģ
    -0.08
     punk
    -0.08
    ãģ¼
    -0.08
     booking
    -0.08
    ney
    -0.08
    æĪ¿ç§Ł
    -0.08
    è´±
    -0.08
    æī¿åĬŀ
    -0.08
    POSITIVE LOGITS
    è¿Ľé©»
    0.09
    éĮ¯
    0.09
    zion
    0.09
    éĶĻ
    0.09
    çĶŁæ´»è´¨éĩı
    0.08
    åŃķæľŁ
    0.08
    _stderr
    0.08
    é¦ĸ次
    0.08
    .Comm
    0.08
    .getActive
    0.08
    Activations Density 0.100%

    No Known Activations