© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23034
    Prev
    Next
    INDEX
    Explanations

    too + adjective

    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
    .har
    -0.10
    å¾Ĺå¾Ī好
    -0.10
    à¹ģà¸Ĺ
    -0.10
    å¾Ī强
    -0.09
    æĽ´å¥½çļĦ
    -0.09
     bestselling
    -0.09
    è§Ħå¾ĭ
    -0.09
     лÑĥÑĩÑĪе
    -0.09
    æĦīå¿«
    -0.09
    hir
    -0.09
    POSITIVE LOGITS
    以èĩ³äºİ
    0.16
    太
    0.12
    太快
    0.11
    /to
    0.11
    太å°ij
    0.10
     too
    0.10
    以åħį
    0.10
    too
    0.10
    太å¤ļ
    0.10
    以èĩ´
    0.09
    Activations Density 0.055%

    No Known Activations