© 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. 20317
    Prev
    Next
    INDEX
    Explanations

    schools and educational institutions

    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
    ande
    -0.10
    çĹ´
    -0.10
    å¤§èµĽ
    -0.09
    enta
    -0.09
    éĶ¦
    -0.09
    éĶ¦æłĩ
    -0.08
    æĨİ
    -0.08
    ientos
    -0.08
    ç²¾éĢī
    -0.08
     ÑĤÑĢ
    -0.08
    POSITIVE LOGITS
    oku
    0.09
     Pur
    0.09
     prox
    0.08
    å®ŀä½ĵ
    0.08
    纯
    0.08
    çļĦä»»åĬ¡
    0.08
    åīįæĸ¹
    0.08
     Lad
    0.08
    åł
    0.08
    åłĤ
    0.08
    Activations Density 0.225%

    No Known Activations