© 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. 24059
    Prev
    Next
    INDEX
    Explanations

    postgreSQL database gem PG

    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
    ãĤĮ
    -0.09
    wolf
    -0.09
    .dtd
    -0.08
    olah
    -0.08
    èĬ®
    -0.08
    ï¸ı
    -0.08
    Toy
    -0.08
    emente
    -0.07
     minut
    -0.07
    гон
    -0.07
    POSITIVE LOGITS
    å¸ģ
    0.11
    è´²
    0.10
    è·Ĺ
    0.09
    è¨ĢãģĪãģ°
    0.09
    uration
    0.09
    æ´Ļ
    0.09
    tern
    0.09
    ãģ¿ãĤĭãģ¨
    0.09
    å®ĮåĸĦ
    0.09
    دت
    0.09
    Activations Density 0.022%

    No Known Activations