© 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. 18071
    Prev
    Next
    INDEX
    Explanations

    Jerry followed by a name

    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
    人士
    -0.10
    nings
    -0.10
    lessly
    -0.09
    åIJĦæł·
    -0.09
     Æ¡n
    -0.09
    á»ĩn
    -0.08
    глав
    -0.08
    èĹľ
    -0.08
    bred
    -0.08
    oes
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģ份
    0.10
    æĢ¿
    0.10
    çĸ½
    0.09
    ×ļ
    0.09
    åIJĪãĤıãģĽ
    0.09
    OptionsMenu
    0.09
    çıº
    0.09
    ãģĦãģĨ
    0.08
     convinc
    0.08
    åĬ¨çĶŁæĪIJ
    0.08
    Activations Density 0.077%

    No Known Activations