© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19630
    Prev
    Next
    INDEX
    Explanations

    free list

    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
    æĻı
    -0.10
    esson
    -0.08
     Hick
    -0.08
    ÑģÑģ
    -0.08
     пÑĢин
    -0.08
    wake
    -0.08
    ç½ijç«Ļ建设
    -0.08
    æĹ¶è¾°
    -0.08
     vic
    -0.08
    家ä½ı
    -0.08
    POSITIVE LOGITS
    æľ´
    0.10
    æŶæķĪ
    0.10
    ×ĵ×£
    0.10
    ç¿ĺ
    0.09
    æĭIJ
    0.09
    æĮĽ
    0.09
    owski
    0.09
    åħ¨åľº
    0.09
    åį³æŶ
    0.09
    缮çļĦåľ°
    0.09
    Activations Density 0.001%

    No Known Activations