© 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. 11930
    Prev
    Next
    INDEX
    Explanations

    entities and organizations

    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
    omm
    -0.10
    漫éķ¿çļĦ
    -0.08
    ä¸įè¿ĩæĺ¯
    -0.08
    éķľ
    -0.08
    åĨħå¤ĸ
    -0.08
    phen
    -0.08
    è¯ı
    -0.08
     Schw
    -0.08
    ä½łèĩªå·±
    -0.08
    æī¿è®¤
    -0.08
    POSITIVE LOGITS
    å·¡åĽŀ
    0.09
    å·¡è§Ĩ
    0.09
    å·¡
    0.08
    å·¡éĢ»
    0.08
    æ¿Ł
    0.08
    uis
    0.08
    çī¹æ´¾
    0.08
    æį¶
    0.08
    æĥ³
    0.08
    itial
    0.08
    Activations Density 0.054%

    No Known Activations