© 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. 48556
    Prev
    Next
    INDEX
    Explanations

    now followed by consequences or new information

    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
    èİ«
    -0.10
     nig
    -0.09
    ä¼į
    -0.09
    ewis
    -0.09
    MO
    -0.09
    elon
    -0.08
    éľ²å¤©
    -0.08
    å¤ļ次
    -0.08
    ifies
    -0.08
    onis
    -0.08
    POSITIVE LOGITS
    æľīæĽ´å¤ļçļĦ
    0.10
    æĽ´å¤ļçļĦ
    0.10
    æĿ¡æ¬¾
    0.10
    å¼¼
    0.09
    æł¼å°Ķ
    0.09
     اÙĦÙħزÙĬد
    0.09
    æĽ´å®¹æĺĵ
    0.09
    è®®æ¡Ī
    0.09
    rou
    0.09
    赶ä¸Ĭ
    0.09
    Activations Density 0.037%

    No Known Activations