© 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. 53683
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    çļĦç¡®
    -0.08
    ä»ĸ们ä¼ļ
    -0.08
    åĪĨå·¥
    -0.08
    Sir
    -0.08
     Blaze
    -0.08
    çĥĽ
    -0.08
    åĪĩæĪIJ
    -0.08
    å·ħå³°
    -0.08
    паÑĤ
    -0.08
    itters
    -0.08
    POSITIVE LOGITS
    åĵij
    0.09
    fully
    0.09
    dummy
    0.09
    æľĢå¤ļçļĦ
    0.08
     ÑĪколÑĮ
    0.08
    æ©Ľ
    0.08
    åĸĨ
    0.08
    ream
    0.08
     вн
    0.08
    lessly
    0.08
    Activations Density 0.014%

    No Known Activations