© 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. 55328
    Prev
    Next
    INDEX
    Explanations

    nuclear related words

    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
    åĴĮæĶ¯æĮģ
    -0.10
    ynet
    -0.10
    诳
    -0.10
    è¶ħé¢Ŀ
    -0.10
    ä¸į满æĦı
    -0.09
    åŁŃ
    -0.09
    .toArray
    -0.09
    anzi
    -0.09
    ç»İ
    -0.09
    ç¼£
    -0.09
    POSITIVE LOGITS
     Nuclear
    0.09
    æł¸
    0.09
     nuclear
    0.09
    ity
    0.09
    oris
    0.09
    lef
    0.09
    LEAR
    0.08
    lus
    0.08
    rosse
    0.08
    inated
    0.08
    Activations Density 0.069%

    No Known Activations