© 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. 62493
    Prev
    Next
    INDEX
    Explanations

    amount of

    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
    çIJĨæĥ³çļĦ
    -0.09
     heck
    -0.08
    ipe
    -0.08
     Vocal
    -0.08
    æµĨ
    -0.08
    utzer
    -0.08
    èĦ¸ä¸Ĭ
    -0.08
    çĺ¦èº«
    -0.08
    .CONFIG
    -0.08
    ä¿Ŀ驾
    -0.08
    POSITIVE LOGITS
     Ñĩего
    0.10
    çĶ³
    0.10
    è¿Ļæĸ¹éĿ¢
    0.10
    åIJĦæĸ¹éĿ¢
    0.10
    黳
    0.09
    å¼Ģå°ģ
    0.09
     everything
    0.09
    çĶ³æĬ¥
    0.09
    æĵħ
    0.09
    éĢĤéĩı
    0.09
    Activations Density 0.106%

    No Known Activations