© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9277
    Prev
    Next
    INDEX
    Explanations

    single

    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¸įåIJĮçļĦ
    -0.09
    imat
    -0.09
    ä¸įä¸Ģæł·çļĦ
    -0.09
     Aires
    -0.09
    ä¸įä»ħä»ħæĺ¯
    -0.08
    æľīä¸įåIJĮçļĦ
    -0.08
    æħ·
    -0.08
    fore
    -0.08
    ä¸įä¸Ģæł·
    -0.08
    rack
    -0.08
    POSITIVE LOGITS
    /single
    0.21
    (single
    0.20
    æĪĸå¤ļ
    0.19
    -single
    0.17
     single
    0.15
    single
    0.15
    .single
    0.14
    tons
    0.14
    .Single
    0.14
     SINGLE
    0.13
    Activations Density 0.172%

    No Known Activations