© 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. 30429
    Prev
    Next
    INDEX
    Explanations

    as simple as

    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
    æľªçŁ¥
    -0.09
    æĬĢå¸Ī
    -0.09
    人士
    -0.09
    妪
    -0.09
    æľĪæľ«
    -0.09
    .imp
    -0.09
     olds
    -0.09
    edly
    -0.09
    æģķ
    -0.09
    nego
    -0.08
    POSITIVE LOGITS
    éĤ£ä¹Īç®Ģåįķ
    0.11
    ä¸Ģåı¥
    0.11
    ä¸Ģåı¥è¯Ŀ
    0.11
    ç®ĢåįķçļĦ
    0.10
    éĢĥéģ¿
    0.10
    /simple
    0.10
    åĩłåı¥
    0.09
    åıªéľĢè¦ģ
    0.09
    åıªè¦ģ
    0.09
    æį¢ä¸ª
    0.09
    Activations Density 0.030%

    No Known Activations