© 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. 944
    Prev
    Next
    INDEX
    Explanations

    thunderstorms

    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
    åİ¢
    -0.10
    åģĥ
    -0.10
    ually
    -0.10
    /legal
    -0.10
    itudes
    -0.09
    ivet
    -0.09
    uur
    -0.09
    æĻ·
    -0.09
    abled
    -0.09
     недо
    -0.08
    POSITIVE LOGITS
    ous
    0.14
    storms
    0.11
    ãģĹãģ¾ãģĨ
    0.10
    lined
    0.09
    suit
    0.09
    ize
    0.09
    neath
    0.09
    çĦ¶æĺ¯
    0.09
    lining
    0.09
    æ²
    0.09
    Activations Density 0.002%

    No Known Activations