© 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. 26356
    Prev
    Next
    INDEX
    Explanations

    word endings (-ness, -tr)

    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
    éĽ¨æ°´
    -0.09
     Printed
    -0.09
    饮éħĴ
    -0.08
    ROID
    -0.08
    åĪĹ
    -0.08
    主ä¹ī
    -0.08
    ç°§
    -0.08
    à¸ģา
    -0.08
    以èī²
    -0.08
    ebin
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķæŶåĢĻ
    0.09
    ãģĦãģ¤ãĤĤ
    0.09
    è´Ŀ壳
    0.09
    éĵ¢
    0.09
    ä¸ĭ游
    0.09
    åIJĮæł·çļĦ
    0.08
    деÑĢжива
    0.08
    åľ°å¸¦
    0.08
    æĹłæĥħ
    0.08
    æīĵå¼ĢäºĨ
    0.08
    Activations Density 0.159%

    No Known Activations