© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9487
    Prev
    Next
    INDEX
    Explanations

    questions starting with "does"

    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
    è°´
    -0.09
     somehow
    -0.09
    æ³®
    -0.09
    ourced
    -0.08
    aint
    -0.08
    tru
    -0.08
    ç¼Ģ
    -0.08
    ãģĦãģĭ
    -0.08
    æĪijæīį
    -0.08
     Som
    -0.08
    POSITIVE LOGITS
    è¿Ļåı¥è¯Ŀ
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.09
    çľ¼çľĭ
    0.09
    лÑĮн
    0.08
    inaire
    0.08
    ãĤĪãģı
    0.08
    æµİ
    0.08
    æĶ¾å°Ħ
    0.08
    fully
    0.08
    ariat
    0.08
    Activations Density 0.030%

    No Known Activations