© 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. 57895
    Prev
    Next
    INDEX
    Explanations

    replaced by

    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
    çļĦçģµéŃĤ
    -0.09
    æĬ±ä½ı
    -0.09
    æ´ģ
    -0.09
    Ñĥз
    -0.08
    è¿ĺèĥ½
    -0.08
    å¥ķ
    -0.08
    çļĦèĢģ
    -0.08
    ä½łè¿ĺ
    -0.08
    åĹĵåŃIJ
    -0.08
    éĺ¡
    -0.08
    POSITIVE LOGITS
    è¶Ĭ
    0.11
    åĹŁ
    0.10
    è¿Ń
    0.10
    spath
    0.09
    æ±Łæ¹ĸ
    0.09
    以人æ°ij
    0.09
    tl
    0.08
    ·»
    0.08
    undef
    0.08
    ç»ŀ
    0.08
    Activations Density 0.018%

    No Known Activations