© 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. 56340
    Prev
    Next
    INDEX
    Explanations

    name changed and renamed

    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
     breakdown
    -0.09
    å¹²éĥ¨
    -0.08
    place
    -0.08
    æĶ¯éħį
    -0.08
    çļĦè®°å¿Ĩ
    -0.08
    便æĺ¯
    -0.08
    åģľæĶ¾
    -0.08
     memoria
    -0.08
    å°±çŁ¥éģĵ
    -0.08
    çľģå¸Ĥ
    -0.07
    POSITIVE LOGITS
    æĽ´åIJį为
    0.16
    æĶ¹ä¸º
    0.14
     Äijá»ķi
    0.13
    æĶ¹æĪIJ
    0.13
    æĺ
    0.11
    æĶ¹
    0.10
    åıĺæĽ´
    0.10
     ë³Ģê²½
    0.10
    .changed
    0.09
    æĽ´æĶ¹
    0.09
    Activations Density 0.238%

    No Known Activations