© 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. 3137
    Prev
    Next
    INDEX
    Explanations

    saying

    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
    ãģĸ
    -0.09
    åĭIJ
    -0.09
    åį§
    -0.08
    еÑģÑĤв
    -0.08
    wan
    -0.08
    åıĻ
    -0.08
    ando
    -0.08
    imon
    -0.08
    ourke
    -0.08
    æĶ¸
    -0.08
    POSITIVE LOGITS
    ä¿Ĺè¯Ŀ说
    0.18
    ä¿Ĺ
    0.14
    ä¸Ģåı¥
    0.13
    è°ļ
    0.13
    éĥ½è¯´
    0.12
    ä¸Ģåı¥è¯Ŀ
    0.12
     saying
    0.12
    說
    0.12
    说éģĵ
    0.12
    说æ³ķ
    0.12
    Activations Density 0.041%

    No Known Activations