© 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. 38447
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    æ¬ł
    -0.09
    иÑĪ
    -0.09
    èİŀ
    -0.09
    éĤij
    -0.09
    ETO
    -0.09
    è¡Ħ
    -0.09
    éģĺ
    -0.09
    rage
    -0.08
    èIJ¥ä¸ļ
    -0.08
    å¢ŀåĢ¼
    -0.08
    POSITIVE LOGITS
     Magnus
    0.09
    失误
    0.09
     Hockey
    0.09
     Lad
    0.09
    èįĴ
    0.08
    aption
    0.08
    LEAR
    0.08
    硬度
    0.08
    åħīèĬĴ
    0.08
    ÑģÑĤеÑĢ
    0.08
    Activations Density 0.009%

    No Known Activations