© 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. 61498
    Prev
    Next
    INDEX
    Explanations

    first or third Sunday/Tuesday

    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
    纷纷
    -0.11
    注æĦıåĬĽ
    -0.11
    å½¹
    -0.10
    Prim
    -0.09
    æĹ¥å¸¸çĶŁæ´»
    -0.09
    WISE
    -0.09
    æĸĭ
    -0.09
    wise
    -0.09
    æľºä½ĵ
    -0.09
     scratch
    -0.09
    POSITIVE LOGITS
    éķľåŃIJ
    0.09
     воÑĤ
    0.09
    кÑĥÑģ
    0.09
     thượng
    0.08
    æĿIJ
    0.08
    æĸ¹è¨Ģ
    0.08
     sober
    0.08
     sö
    0.08
     zs
    0.07
    gers
    0.07
    Activations Density 0.027%

    No Known Activations