© 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. 4538
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    metic
    -0.10
    ÙĦات
    -0.09
    hone
    -0.09
    å¿ĥåĬ¨
    -0.09
    alla
    -0.09
    åĬ¨åijĺ
    -0.09
    è°ĥåĬ¨
    -0.09
    ä¼į
    -0.09
     pits
    -0.08
    ç¬Ħ
    -0.08
    POSITIVE LOGITS
    à¸IJาà¸Ļ
    0.09
    çļĦæĪ¿åŃIJ
    0.09
    ../../../
    0.09
     Cone
    0.09
    åģ¿
    0.08
    spe
    0.08
    ally
    0.08
    sandbox
    0.08
    olf
    0.08
    cken
    0.08
    Activations Density 0.006%

    No Known Activations