© 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. 39331
    Prev
    Next
    INDEX
    Explanations

    software license terms

    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
    Coach
    -0.09
     Sparks
    -0.09
    人èĦī
    -0.09
    ament
    -0.09
    æ»ijéĽª
    -0.08
    .libs
    -0.08
    ëįĺ
    -0.08
    âŁ¹
    -0.08
    èŀį
    -0.08
     Coach
    -0.08
    POSITIVE LOGITS
     Bris
    0.09
    å£ķ
    0.09
    è¿ĺ以为
    0.08
     ERR
    0.08
    åħįçĸ«
    0.08
    åĨĻä½ľ
    0.08
    大桥
    0.08
    误导
    0.08
    åıĮéĩį
    0.08
    èĤ¡ä»·
    0.08
    Activations Density 0.009%

    No Known Activations