© 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. 59093
    Prev
    Next
    INDEX
    Explanations

    rock types and geology

    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
    ç©·
    -0.09
    éĢļé£İ
    -0.09
    erate
    -0.09
    éĹ´éļĻ
    -0.09
    okin
    -0.09
    è´¥
    -0.08
    chron
    -0.08
    éĻįæ°´
    -0.08
    çľ¼çľĭ
    -0.08
    룰
    -0.08
    POSITIVE LOGITS
    åħļçļĦé¢Ĩ导
    0.09
    åĬĪ
    0.09
    ä»Ĩ
    0.09
     fri
    0.08
    å§Ĭ妹
    0.08
    ä»ħä¾Ľ
    0.08
    ought
    0.08
    ä¸ĭ游
    0.08
    Atlas
    0.08
     League
    0.08
    Activations Density 0.063%

    No Known Activations