© 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. 20267
    Prev
    Next
    INDEX
    Explanations

    given name meaning

    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
    æīĢåľ¨
    -0.09
    ç«Ļ
    -0.09
    åIJĦèĩª
    -0.08
     unknown
    -0.08
    amas
    -0.08
     Unknown
    -0.08
    ly
    -0.08
    à¸Ļาม
    -0.08
    ä¿Ĺ称
    -0.08
     Known
    -0.08
    POSITIVE LOGITS
    大åħ¨
    0.09
    odos
    0.09
    abwe
    0.09
    æ¸ħåĩī
    0.09
    ór
    0.09
     plate
    0.09
    å½ĵçĦ¶
    0.08
    æĢ»ç®Ĺ
    0.08
    天èµĭ
    0.08
    ayar
    0.08
    Activations Density 0.071%

    No Known Activations