© 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. 824
    Prev
    Next
    INDEX
    Explanations

    horse and hound breeds

    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
     же
    -0.09
    éħ¥
    -0.09
    ä¼
    -0.09
    椴
    -0.09
    èĮ¸
    -0.08
    å¹¼ç¨ļ
    -0.08
    è¿ijè·Ŀ离
    -0.08
    ulled
    -0.08
    ä¸įå¿ħ
    -0.08
    çĽį
    -0.08
    POSITIVE LOGITS
    ToF
    0.10
    edly
    0.10
    pow
    0.09
    ç²¾
    0.09
    pod
    0.09
    á¸ı
    0.09
    egment
    0.09
    æºħ
    0.09
     wah
    0.09
    بÙĪ
    0.08
    Activations Density 0.006%

    No Known Activations