© 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. 6208
    Prev
    Next
    INDEX
    Explanations

    describing counts or states

    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
    çIJı
    -0.10
    eus
    -0.09
    jem
    -0.09
    åŀĤ
    -0.09
    çĶ»çĶ»
    -0.09
     Franken
    -0.08
    nton
    -0.08
    inea
    -0.08
     slate
    -0.08
    åıĤèĢĥèµĦæĸĻ
    -0.08
    POSITIVE LOGITS
    cope
    0.10
    mer
    0.09
    odic
    0.08
     обоÑĢÑĥд
    0.08
    æĪij家
    0.08
    rad
    0.08
    oyo
    0.08
    主人
    0.08
    presso
    0.08
    ç»·
    0.08
    Activations Density 0.193%

    No Known Activations