© 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. 64092
    Prev
    Next
    INDEX
    Explanations

    type of cheese

    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
    åĩ¸
    -0.09
    ела
    -0.09
    ä¸Ģå¥Ĺ
    -0.08
    çĶŁæĢķ
    -0.08
    é»Ħæĺı
    -0.08
    æĿī
    -0.08
    åĸĿæ°´
    -0.08
    åģľä¸ĭ
    -0.08
    é¦ĭ
    -0.08
    orre
    -0.08
    POSITIVE LOGITS
    /raw
    0.12
     raw
    0.11
    ä½ľä¸ºä¸Ģç§į
    0.11
    åİŁæĸĻ
    0.11
    éĤĻ
    0.09
    è¿Ļ个è¡Įä¸ļ
    0.09
    å½¢çĬ¶
    0.09
    èĩ¾
    0.09
    обÑĢаÐ
    0.08
     native
    0.08
    Activations Density 0.160%

    No Known Activations