© 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. 22073
    Prev
    Next
    INDEX
    Explanations

    ready, active, dispatched, deliver

    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
    误ä¼ļ
    -0.10
    对éĿ¢
    -0.10
    ä¿¡èµĸ
    -0.09
    ishi
    -0.09
    uga
    -0.09
     Stam
    -0.09
    uts
    -0.09
    ä¼łæŁĵ
    -0.08
    isha
    -0.08
    alto
    -0.08
    POSITIVE LOGITS
    ç»ĻæĤ¨
    0.09
    绾
    0.09
    -ready
    0.08
    ä»Ģä¹Īæł·
    0.08
    羣çIJĨ
    0.08
    ä¿Ł
    0.08
    å®ŀçī©
    0.08
    дав
    0.08
    æ´¾
    0.08
    款
    0.08
    Activations Density 0.052%

    No Known Activations