© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36246
    Prev
    Next
    INDEX
    Explanations

    Canada

    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
    迪æĭľ
    -0.11
    ried
    -0.10
    西äºļ
    -0.10
    å°ijãģªãģĦ
    -0.09
    æįŁèĢĹ
    -0.09
    æĥ³èµ·æĿ¥
    -0.09
    èł²
    -0.09
    ä»ĸå¦Ī
    -0.09
    ço
    -0.09
    uste
    -0.09
    POSITIVE LOGITS
    éĨį
    0.09
    æĬ¹
    0.08
     Organisation
    0.08
    ä¸įçĦ¶
    0.08
    Encoding
    0.08
    걸
    0.08
    åİ
    0.08
    æĮĤ
    0.08
    èĽĩ
    0.08
    å¥ī
    0.08
    Activations Density 0.002%

    No Known Activations