© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 700
    Prev
    Next
    INDEX
    Explanations

    ping connectivity

    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
    Negative Logits
    annes
    -0.09
    untime
    -0.09
    ä¹¾
    -0.09
    ÅĽci
    -0.09
    ÑģÑĤÑĢа
    -0.09
     som
    -0.08
    éĨº
    -0.08
    вен
    -0.08
    æµģåĬ¨
    -0.08
    æIJ¬è¿IJ
    -0.08
    POSITIVE LOGITS
    HING
    0.09
    .ping
    0.09
    ileo
    0.08
    大çļĦ
    0.08
     ping
    0.08
    åıĭè°Ĭ
    0.08
    æłĩçļĦ
    0.08
    resp
    0.08
    ä¸Ģä¸ĭ
    0.08
    gu
    0.08
    Activations Density 0.038%

    No Known Activations