© 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. 57409
    Prev
    Next
    INDEX
    Explanations

    small items, minute, smaller

    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
    æĴŀ
    -0.10
    å®ŀæĪĺ
    -0.09
     fore
    -0.09
    建éĢł
    -0.08
    常说
    -0.08
    ressed
    -0.08
    æĹ¥æľ¬äºº
    -0.08
     Growth
    -0.08
    æģ°
    -0.08
    åĩºåıij
    -0.08
    POSITIVE LOGITS
    è¾ĥ大
    0.11
    è¾ĥå°ı
    0.11
    çī©ä»¶
    0.10
    è´¬åĢ¼
    0.10
    è¾ĥ大çļĦ
    0.10
    éªIJ
    0.10
    éļ¾ä»¥
    0.09
    è¾ĥ
    0.09
    æĸ°ä¸ī
    0.09
    大å®ĹåķĨåĵģ
    0.09
    Activations Density 0.127%

    No Known Activations