© 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. 47524
    Prev
    Next
    INDEX
    Explanations

    Mr. followed by a name

    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
    è¿Ļä¸ĢçĤ¹
    -0.10
    èĩªå¦Ĥ
    -0.09
    è¿ĻçĤ¹
    -0.08
    å¸Ŀ
    -0.08
    è¿Ļ对
    -0.08
    -minded
    -0.08
    iert
    -0.08
    æĤĮ
    -0.08
    ais
    -0.08
     hereby
    -0.08
    POSITIVE LOGITS
    że
    0.10
    ÌĢ
    0.09
     Bun
    0.09
    .chapter
    0.09
    ãĥĸãĥ©
    0.09
    ðŁı»
    0.09
    们çļĦ
    0.09
     jednak
    0.09
    ÑĩеÑĤ
    0.08
    çļĦæĪ¿åŃIJ
    0.08
    Activations Density 0.021%

    No Known Activations