© 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. 40109
    Prev
    Next
    INDEX
    Explanations

    visual memory and features

    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
    æĮĤçīĮ
    -0.11
    èľĤ
    -0.10
    æŀ§
    -0.10
    æĸ°ä¸ī
    -0.09
    没äºĭ
    -0.09
    æĥĩ
    -0.09
    èŁ¾
    -0.09
    hed
    -0.09
    ovsky
    -0.09
    .NAME
    -0.09
    POSITIVE LOGITS
    åĢ¡
    0.10
    梦
    0.09
    ç¼Ŀ
    0.09
    躲éģ¿
    0.08
    å¼Ĥè®®
    0.08
    è¿ijäºĽå¹´
    0.08
    åŀ¢
    0.08
     Gardner
    0.08
    hydr
    0.08
    illa
    0.08
    Activations Density 0.122%

    No Known Activations