© 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. 22393
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    اسÙħ
    -0.09
    eko
    -0.09
    ille
    -0.09
     Chá»ĭ
    -0.09
    iking
    -0.09
    ILLE
    -0.08
    天é¹ħ
    -0.08
    ç«Ļåľ¨
    -0.08
     sake
    -0.08
    ÑĨен
    -0.08
    POSITIVE LOGITS
    湫
    0.10
    ä¸ĭæĿ¥çļĦ
    0.09
    çĶŁäº§è½¦éĹ´
    0.09
    åŀĽ
    0.09
    åĽ¢ç»ĵ
    0.09
    åĪĽå§ĭ
    0.09
    åŁĿ
    0.09
    territ
    0.09
    æ¯Ķäºļ
    0.09
    æIJŃ
    0.09
    Activations Density 0.068%

    No Known Activations