© 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. 16647
    Prev
    Next
    INDEX
    Explanations

    return values or calculation

    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
    emos
    -0.09
    éķ¿å¤§
    -0.09
    ForResult
    -0.09
    gere
    -0.08
    æ·±å±Ĥ
    -0.08
    åĬ¬
    -0.08
    /API
    -0.08
    è´¯
    -0.08
    åĮ»ç§ij大åѦ
    -0.08
    貫
    -0.08
    POSITIVE LOGITS
    æĪij说
    0.09
    agli
    0.09
     Wah
    0.09
    rog
    0.09
    æ¯įæł¡
    0.08
    ãģ¿ãģ¦
    0.08
    ä¸įé«ĺ
    0.08
    å°ıç»Ħ
    0.08
    ersive
    0.08
    åįģ足
    0.08
    Activations Density 0.009%

    No Known Activations