© 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. 3805
    Prev
    Next
    INDEX
    Explanations

    which includes

    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
    ä¸ĢæĿ¡é¾Ļ
    -0.10
    èĿĩ
    -0.10
    çĦķ
    -0.09
    ä¼ī
    -0.09
    ä¸Ģèīĺ
    -0.09
    ä¸Ŀ绸
    -0.08
    ä¸ĢåĪĨéĴŁ
    -0.08
    åľ°ä¸ĭ
    -0.08
    ä¼½
    -0.08
    æĪIJ为ä¸ŃåĽ½
    -0.08
    POSITIVE LOGITS
    åĮħæĭ¬
    0.12
    涵çĽĸ
    0.09
    å¾Ī大
    0.09
    MAS
    0.09
    åħ¶ä¸ŃåĮħæĭ¬
    0.09
    å¤ļæķ°
    0.09
    è¦ĨçĽĸéĿ¢
    0.09
    大éĥ¨åĪĨ
    0.08
     majority
    0.08
    ä¹Łä¸įæķ¢
    0.08
    Activations Density 0.075%

    No Known Activations