© 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. 62745
    Prev
    Next
    INDEX
    Explanations

    an introduction

    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
    oko
    -0.11
    ä¹İ
    -0.10
    ductor
    -0.09
    æ¾¹
    -0.09
    大å¦Ī
    -0.08
    çIJIJ
    -0.08
    .metro
    -0.08
    æŃ£æĸĩ
    -0.08
    çĦī
    -0.08
    ÇĴ
    -0.08
    POSITIVE LOGITS
    çĸµ
    0.09
    æĹłç¼ĺ
    0.09
    aires
    0.09
    ethe
    0.08
    ires
    0.08
    ymes
    0.08
    yna
    0.08
    å¾Ĺ天
    0.08
     sling
    0.08
     santa
    0.08
    Activations Density 0.020%

    No Known Activations