© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17613
    Prev
    Next
    INDEX
    Explanations

    United States

    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
    éĤ£è¾¹
    -0.08
    é¢ijéģĵ
    -0.08
     bows
    -0.08
    è¯įæĿ¡
    -0.08
    á»įn
    -0.08
    BERT
    -0.08
    å¾Ĺèµ·
    -0.08
    åįıåĬŀ
    -0.08
    usc
    -0.07
    _own
    -0.07
    POSITIVE LOGITS
    èµ°åľ¨
    0.11
    åIJĦ级
    0.10
    æĥ°
    0.10
    æİĸ
    0.10
     abstract
    0.09
    åŁł
    0.09
    ×ķ×ĺ
    0.09
    æĶ¾çľ¼
    0.09
     Ske
    0.09
    çļĦ家åºŃ
    0.09
    Activations Density 0.252%

    No Known Activations