© 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. 47483
    Prev
    Next
    INDEX
    Explanations

    representation, represented, representative

    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
    æķħå±ħ
    -0.10
    禳
    -0.09
    å¢ĥ
    -0.09
    AXB
    -0.09
    å¤ķ
    -0.09
    å¾Ĺ天
    -0.09
    å¼Ĭ
    -0.09
    æĺ¯å¯¹
    -0.09
    axies
    -0.09
    첨
    -0.09
    POSITIVE LOGITS
    代表
    0.23
    代表æĢ§
    0.21
     representation
    0.20
     Representation
    0.18
     represented
    0.17
    为代表
    0.17
     representative
    0.17
    representation
    0.16
    Represent
    0.16
     Represent
    0.16
    Activations Density 0.093%

    No Known Activations