© 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. 56176
    Prev
    Next
    INDEX
    Explanations

    sixteenth century

    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
     legion
    -0.08
     haus
    -0.08
    èĢķèĢĺ
    -0.08
     gói
    -0.08
    xda
    -0.08
     дол
    -0.08
    æĹ¥çĶµ
    -0.08
    èģĶåIJĪ
    -0.08
    Æ¡n
    -0.08
    èĮĤ
    -0.08
    POSITIVE LOGITS
    æĬķèµĦé¢Ŀ
    0.10
    æĺİæľĿ
    0.09
    没éĴ±
    0.09
     Moscow
    0.09
    ç»Ī身
    0.09
    ä¸ĢçĶŁ
    0.08
    ä¸įæĺ¯ä¸Ģ个
    0.08
    æĺİ代
    0.08
     Fuji
    0.08
    çł·
    0.08
    Activations Density 0.207%

    No Known Activations