© 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. 60873
    Prev
    Next
    INDEX
    Explanations

    vary from X to Y

    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
    æĦŁåħ´è¶£çļĦ
    -0.09
    letic
    -0.07
     Lud
    -0.07
    ERA
    -0.07
    l
    -0.07
    ä¸Ŀ绸ä¹ĭè·¯
    -0.07
    è¿Ļæł·ä¸Ģ个
    -0.07
    æĭŁ
    -0.07
    1
    -0.07
    å¼¼
    -0.07
    POSITIVE LOGITS
    æŀķ
    0.11
    ç¥Ī祷
    0.10
    åľºåIJĪ
    0.10
    åľ°åĮº
    0.10
    ToSelector
    0.10
    obel
    0.10
    家ä¼Ļ
    0.09
    criptor
    0.09
    åIJģ
    0.09
    éĩįä¸Ńä¹ĭéĩį
    0.09
    Activations Density 0.013%

    No Known Activations