© 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. 31308
    Prev
    Next
    INDEX
    Explanations

    specific technical terms or definitions

    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¨ä»½
    -0.08
     phiếu
    -0.08
    ä½İè°ĥ
    -0.08
     Gree
    -0.08
    åľ£è¯ŀ
    -0.08
    íĹĮ
    -0.08
    ç»ĥ
    -0.07
    åķ¬
    -0.07
    .Cap
    -0.07
    æ¤ħ
    -0.07
    POSITIVE LOGITS
    åģļ大
    0.11
    åľ¨åºĬä¸Ĭ
    0.10
    å¤§åĽ½
    0.10
    åĽ½åľŁ
    0.10
    åľ¨åľ°ä¸Ĭ
    0.09
    åĽłä¸ºä»ĸ们
    0.09
    æĢ§åij½
    0.09
    enet
    0.09
     kin
    0.09
    åģļå¾Ĺ
    0.09
    Activations Density 0.038%

    No Known Activations