© 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. 16911
    Prev
    Next
    INDEX
    Explanations

    dozen

    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
    utan
    -0.11
    ollections
    -0.10
    åİ
    -0.09
    å¥
    -0.09
    éŃ
    -0.09
    ammer
    -0.08
    åijĺ
    -0.08
    haps
    -0.08
     vast
    -0.08
    æ²Į
    -0.08
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.10
    ä¼ĺçĤ¹
    0.10
    人éĥ½
    0.09
    ä¹ĥèĩ³
    0.09
    çľģ份
    0.09
    æĪĸå¤ļ
    0.09
    æī°
    0.09
    åı±
    0.08
    jang
    0.08
    æĺ¥ç§ĭ
    0.08
    Activations Density 0.011%

    No Known Activations