© 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. 24085
    Prev
    Next
    INDEX
    Explanations

    in [phrase]

    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
    çµ±
    -0.10
    .DataTable
    -0.10
    atrice
    -0.10
    åµĩ
    -0.09
    绣
    -0.09
     ведÑĮ
    -0.09
    å¼Ģæľº
    -0.09
    å¼ĢæĶ¾å¼ı
    -0.09
    麻çĹ¹
    -0.09
    สà¸Ļ
    -0.09
    POSITIVE LOGITS
     gre
    0.08
    è®´
    0.07
    lam
    0.07
    alone
    0.07
    æłĹ
    0.07
     quint
    0.07
    åıĸãĤĬ
    0.07
    Ñħа
    0.07
    人æ°ij群ä¼Ĺ
    0.07
    .extent
    0.07
    Activations Density 0.060%

    No Known Activations