© 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. 58598
    Prev
    Next
    INDEX
    Explanations

    gaming, treasures, rounds, pockets

    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
    并åIJij
    -0.10
    çIJĨæĢ§
    -0.09
    ogle
    -0.09
    ä¿¡çĶ¨åį¡
    -0.09
    iker
    -0.09
     sty
    -0.08
    æĺ§
    -0.08
    é«ĺ强度
    -0.08
    æĬ¥å¤į
    -0.08
    èħł
    -0.08
    POSITIVE LOGITS
    айл
    0.09
    伸æīĭ
    0.09
     lif
    0.08
     chance
    0.08
    ä¸Ģç»ı
    0.08
    好è¿IJ
    0.08
    favor
    0.08
    çĨŁ
    0.08
    æīij
    0.08
    Hum
    0.08
    Activations Density 0.039%

    No Known Activations