© 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. 51353
    Prev
    Next
    INDEX
    Explanations

    Dancing With the Stars

    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
    èįī
    -0.10
    als
    -0.10
    ä¸įèµ·
    -0.09
    hek
    -0.09
     ÑģоглаÑģ
    -0.08
     WON
    -0.08
    Registrar
    -0.08
    ä¸ĸä¿Ĺ
    -0.08
    æĪIJåĬŁçļĦ
    -0.08
     gan
    -0.08
    POSITIVE LOGITS
    æĬ±
    0.11
    auge
    0.09
    æľ
    0.09
    cv
    0.09
    NonQuery
    0.09
    鼩
    0.09
    å°ıå¿ĥ翼翼
    0.09
    æ²½
    0.09
    åĵĹ
    0.08
    è¬Ģ
    0.08
    Activations Density 0.001%

    No Known Activations