© 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. 33388
    Prev
    Next
    INDEX
    Explanations

    license or terms

    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
    å¿ł
    -0.09
     Mas
    -0.09
    é¢ģå¸ĥ
    -0.09
     Museum
    -0.09
    æ»ĭåij³
    -0.09
    éļ¶å±ŀ
    -0.09
    åľ°ä¸ĭ
    -0.09
    人åĬĽ
    -0.09
    GLOSS
    -0.08
    åįļçī©é¦Ĩ
    -0.08
    POSITIVE LOGITS
    åĶ¤
    0.09
    Êĭ
    0.09
    ully
    0.09
    åħ¬ç¤º
    0.08
    .transitions
    0.08
    caffold
    0.08
    .deep
    0.08
    ä¸İåħ¶ä»ĸ
    0.08
    owers
    0.08
    à¨Ĩ
    0.08
    Activations Density 0.001%

    No Known Activations