© 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. 18115
    Prev
    Next
    INDEX
    Explanations

    action-packed

    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
    ä¸Ģ年级
    -0.09
    æĸ°åŁİ
    -0.09
    ÂŃing
    -0.09
    ments
    -0.09
    noch
    -0.09
    .mainloop
    -0.08
    ings
    -0.08
    æł·åŃIJ
    -0.08
    çĨ¨
    -0.08
    plies
    -0.08
    POSITIVE LOGITS
    å¥
    0.10
    ÙĦÙĬÙĦ
    0.09
    еÑģÑĤ
    0.09
    /live
    0.08
    åIJĦ个æĸ¹éĿ¢
    0.08
    nier
    0.08
    UAL
    0.08
    .DialogInterface
    0.08
    uria
    0.08
    ست
    0.08
    Activations Density 0.007%

    No Known Activations