© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38888
    Prev
    Next
    INDEX
    Explanations

    syndicate or syndicated

    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
    è¸Ŀ
    -0.09
    ãĤ¢ãĥ¼
    -0.09
    éĤ£ä¹Īå¤ļ
    -0.09
    表çĻ½
    -0.09
    ä¹ĭ家
    -0.09
    éĶµ
    -0.09
    é«ĭ
    -0.08
    çļĦçĶ»éĿ¢
    -0.08
    ÑģÑı
    -0.08
     Albums
    -0.08
    POSITIVE LOGITS
    åĨ
    0.10
     synd
    0.09
    opoly
    0.08
    å¦ģ
    0.08
    oston
    0.08
    /Linux
    0.08
    rus
    0.08
    åĮĸçļĦ
    0.08
    оÑĢ
    0.08
    ization
    0.08
    Activations Density 0.006%

    No Known Activations