© 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. 62079
    Prev
    Next
    INDEX
    Explanations

    preceding or indicating something prior

    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
    å¸Ń
    -0.10
    ừ
    -0.10
    é¦ĸ次
    -0.09
    åĩĨæŶ
    -0.09
    ertino
    -0.09
    å°Ħ
    -0.09
    .wik
    -0.09
    olon
    -0.09
    olk
    -0.08
    leck
    -0.08
    POSITIVE LOGITS
    èĢħçļĦ
    0.13
    èĢĮåIJİ
    0.10
    ä¸ĢæĹ¥
    0.09
    ç»ĻäºĨæĪij
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    iu
    0.08
     Ñģобой
    0.08
    à¸ģารà¸Ĺำ
    0.08
    漫éķ¿çļĦ
    0.08
    ä¸ĢçĤ¹ä¹Łä¸į
    0.08
    Activations Density 0.037%

    No Known Activations