© 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. 31981
    Prev
    Next
    INDEX
    Explanations

    technical components and specifications

    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
    æĨĭ
    -0.11
    æ©ĺ
    -0.10
    çľĭ好
    -0.10
    平淡
    -0.10
    çľĭäºĨä¸Ģ
    -0.09
    ese
    -0.09
    æ§Ł
    -0.09
    èĵ¦
    -0.09
    æĮĸæİĺ
    -0.08
    å¹³æĿ¿
    -0.08
    POSITIVE LOGITS
    INCT
    0.10
    Ñįм
    0.09
    æ¹ĸåĮĹ
    0.09
    éĵľ
    0.09
    DED
    0.09
    å¼Ĥåľ°
    0.09
     Murdoch
    0.08
    çłĶ究æĪIJæŀľ
    0.08
    åİŁåĪĽ
    0.08
     bells
    0.08
    Activations Density 0.057%

    No Known Activations