© 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. 16542
    Prev
    Next
    INDEX
    Explanations

    documentary production company

    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
    entar
    -0.08
     [...]↵↵
    -0.07
    à¸Ħà¸Ń
    -0.07
     eventual
    -0.07
     ?
    -0.07
     [âĢ¦
    -0.07
    å°¤åħ¶
    -0.06
    ä¸ĭä¸Ģ
    -0.06
     Nat
    -0.06
    å®ļåIJij
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·åģļ
    0.10
    æŀķ头
    0.09
    å¹Ķ
    0.09
    ãn
    0.09
    为ä¹ĭ
    0.09
    otton
    0.09
    éĺĶ
    0.09
    åĭģ
    0.08
    以ä¸ĭç®Ģ称
    0.08
    Iterations
    0.08
    Activations Density 5.365%

    No Known Activations