© 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. 9931
    Prev
    Next
    INDEX
    Explanations

    questions about outcomes and methods

    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
    rib
    -0.09
    ä¸Ī
    -0.08
    çĦķåıij
    -0.08
     оÑģнов
    -0.08
     pob
    -0.08
    æ²¥
    -0.08
     smack
    -0.08
    临港
    -0.08
     none
    -0.08
    éķ¶
    -0.08
    POSITIVE LOGITS
    çļĤ
    0.10
    群éĩĮ
    0.09
    æģ¶æĦı
    0.09
    ä¸ĢæŶ
    0.09
     lẫn
    0.09
    thouse
    0.09
    ARI
    0.09
    èĴĮ
    0.09
    忾
    0.08
    enta
    0.08
    Activations Density 0.040%

    No Known Activations