© 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. 7756
    Prev
    Next
    INDEX
    Explanations

    making decisions or taking action

    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
    çİ°è¡Į
    -0.08
    -fi
    -0.08
     vas
    -0.08
    æĿĥå¨ģ
    -0.08
    ality
    -0.08
    æĽ´æĺ¯
    -0.08
    åĪĿ次
    -0.08
    享åıĹ
    -0.08
    çľĭ好
    -0.08
     Haram
    -0.08
    POSITIVE LOGITS
     accordingly
    0.24
    缸åºĶ
    0.21
    缸åºĶçļĦ
    0.21
    æį®æѤ
    0.20
    éļıä¹ĭ
    0.15
     Accordingly
    0.15
     entsprech
    0.13
    åĬłä»¥
    0.13
    çĶ±æѤ
    0.13
    åIJĪéĢĤ
    0.12
    Activations Density 0.105%

    No Known Activations