© 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. 55456
    Prev
    Next
    INDEX
    Explanations

    services, and integration

    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
    åĨį说
    -0.11
    åģĥ
    -0.10
    åı«åģļ
    -0.09
    веÑģÑĤ
    -0.09
    åħ³æ³¨åº¦
    -0.09
    ìĺ
    -0.08
    大åĶIJ
    -0.08
    ä¸ŃåĽ½ä¼ģä¸ļ
    -0.08
    è£ħéħįå¼ı
    -0.08
    çļĦçĬ¶æĢģ
    -0.08
    POSITIVE LOGITS
    常年
    0.10
    ç«Ń
    0.10
    ä½ĵ系建设
    0.09
    æĵħéķ¿
    0.09
    代
    0.09
    owski
    0.09
    æĭİ
    0.09
    建档
    0.08
    ä»»ä½ķå½¢å¼ı
    0.08
    åħ¨æĸ¹ä½į
    0.08
    Activations Density 0.130%

    No Known Activations