© 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. 61449
    Prev
    Next
    INDEX
    Explanations

    interpret, read, or imagine

    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
    å¾ĹçŁ¥
    -0.09
     gent
    -0.09
     Berger
    -0.08
    kl
    -0.08
    æĨ©
    -0.08
    çĻ»
    -0.08
    èģĮ
    -0.08
    rowse
    -0.08
     verb
    -0.08
    esty
    -0.08
    POSITIVE LOGITS
    æĬ¹
    0.10
    解读
    0.10
    æĪIJ份
    0.10
    èģĶæĥ³
    0.09
    æľªæĪIJ
    0.09
    æ·»
    0.09
    oji
    0.09
    eron
    0.09
    æĦ¿
    0.09
    åĽŀåİ»
    0.09
    Activations Density 0.073%

    No Known Activations