© 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. 50257
    Prev
    Next
    INDEX
    Explanations

    logout paths

    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
     arrang
    -0.10
    å±ģ
    -0.10
    çŀ»
    -0.09
    ä»Ģä¹Īéĥ½ä¸į
    -0.09
    å§ĵ
    -0.09
    æĭ¯
    -0.09
    èĨĬ
    -0.09
    æĹ¥æĬ¥éģĵ
    -0.09
    interp
    -0.09
    è£Ĵ
    -0.09
    POSITIVE LOGITS
    ButtonTitles
    0.10
    rey
    0.10
    íĥĪ
    0.10
    èIJ½
    0.10
    urai
    0.09
    è¿Ļåıª
    0.09
     кÑĥлÑĮÑĤÑĥÑĢÑĭ
    0.09
    ÕĶ
    0.08
    ciÄħ
    0.08
    emed
    0.08
    Activations Density 0.006%

    No Known Activations