© 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. 6178
    Prev
    Next
    INDEX
    Explanations

    characters, strings, offsets

    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
    pec
    -0.10
    ç½²
    -0.09
    VILLE
    -0.09
    PEC
    -0.08
    æįĤ
    -0.08
    eda
    -0.08
    oro
    -0.08
    ÑĭÑĪ
    -0.08
    对èĩªå·±çļĦ
    -0.08
    orest
    -0.08
    POSITIVE LOGITS
    acters
    0.10
    acer
    0.10
    æĪijæīį
    0.10
    æľīä»»ä½ķ
    0.09
    太å¤ļçļĦ
    0.09
    lotte
    0.09
    ACTER
    0.09
    åı¯éĢļè¿ĩ
    0.09
    åªļ
    0.09
    akter
    0.09
    Activations Density 0.060%

    No Known Activations