© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52184
    Prev
    Next
    INDEX
    Explanations

    predictions and forecasts

    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
     fla
    -0.09
    æµ®
    -0.08
    çªģåıij
    -0.08
    ãģĹãģ
    -0.08
    æį¢åıĸ
    -0.08
    astr
    -0.08
    é²ģ
    -0.08
    社ä¼ļèµĦæľ¬
    -0.08
    æĿł
    -0.08
     клÑĥб
    -0.08
    POSITIVE LOGITS
    é¢Ħæµĭ
    0.27
    é¢Ħè¨Ģ
    0.25
    å±ķæľĽ
    0.22
     пÑĢогноз
    0.20
     predictions
    0.19
     prediction
    0.19
    é¢ĦæĬ¥
    0.19
    å¯¹æľªæĿ¥
    0.18
    é¢Ħè§ģ
    0.17
     predicts
    0.17
    Activations Density 0.064%

    No Known Activations