© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8500
    Prev
    Next
    INDEX
    Explanations

    last names and "and"

    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
    声éģĵ
    -0.10
    веÑģÑĤи
    -0.09
    BCM
    -0.09
    æİł
    -0.09
    声åĵį
    -0.09
    æ´¹
    -0.08
    åĸĩåıŃ
    -0.08
    vest
    -0.08
    麾
    -0.08
    zeigen
    -0.08
    POSITIVE LOGITS
    åŀĤ
    0.08
    inks
    0.08
    éĻIJ
    0.08
     nhỼ
    0.08
    åı¯æĥľ
    0.08
     cig
    0.08
    ä¸įæ¸ħæ¥ļ
    0.08
    å£
    0.08
    éĤ¦
    0.08
    åħ¼é¡¾
    0.08
    Activations Density 0.028%

    No Known Activations