© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36317
    Prev
    Next
    INDEX
    Explanations

    spoken by

    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
    éĵ©
    -0.09
    çªģåĩºéĹ®é¢ĺ
    -0.09
    åIJĦæĸ¹éĿ¢
    -0.09
    éĵĽ
    -0.09
    awai
    -0.09
    é£İæ°Ķ
    -0.09
    åįķ项
    -0.09
     bull
    -0.09
    اÙĨا
    -0.08
    ANEL
    -0.08
    POSITIVE LOGITS
    人çĶŁ
    0.10
    ï¾ŀ
    0.10
    éķ¿æ±Ł
    0.09
    iert
    0.09
    èµ·åºĬ
    0.08
    verted
    0.08
    å°ıåºĹ
    0.08
    æĸ°å¨ĺ
    0.08
    æ¯ıä¸Ģ天
    0.08
    éľİ
    0.08
    Activations Density 0.005%

    No Known Activations