© 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. 7636
    Prev
    Next
    INDEX
    Explanations

    angel or angels

    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
    æµ£
    -0.10
    深度èŀįåIJĪ
    -0.10
     ngu
    -0.10
     Mori
    -0.09
    ipa
    -0.09
     Poison
    -0.09
     паÑĢÑĤи
    -0.09
    ç»Ļèĩªå·±
    -0.09
    æѧ
    -0.09
    vil
    -0.09
    POSITIVE LOGITS
    天使
    0.15
    ç¥ŀä»Ļ
    0.12
    éĻį
    0.12
    ç¿ħèĨĢ
    0.12
    å¥
    0.11
    çľ·
    0.11
     angels
    0.11
    åłķ
    0.10
     Angels
    0.10
    angel
    0.10
    Activations Density 0.056%

    No Known Activations