© 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. 53072
    Prev
    Next
    INDEX
    Explanations

    so perfect, so real, so much

    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
    ibal
    -0.09
    èĹ©
    -0.08
    olec
    -0.08
     двиг
    -0.08
    çħľ
    -0.08
    åĪ°æŶåĢĻ
    -0.08
    æģķ
    -0.08
    /reference
    -0.08
    ìĬµ
    -0.08
    åħijçİ°
    -0.08
    POSITIVE LOGITS
    太å°ij
    0.11
    éĤ£ä¹Ī容æĺĵ
    0.10
    æĹłéĻIJ
    0.10
     Prot
    0.10
    为人
    0.09
    éĤ£ä¹Īå¤ļ
    0.09
    Äħż
    0.09
    ä¸įåħĭ
    0.09
    EMAIL
    0.09
    æĬĵ好
    0.09
    Activations Density 0.021%

    No Known Activations