© 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. 4008
    Prev
    Next
    INDEX
    Explanations

    improved, improvement, faster

    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
    å½¹
    -0.10
     пÑĢоиÑģ
    -0.09
    pcs
    -0.09
    æģĥ
    -0.09
    ding
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    æļ¨
    -0.08
    à¹Ĥà¸Ľà¸£à¸Ķ
    -0.08
    å°ıèħ¿
    -0.08
    aks
    -0.08
    POSITIVE LOGITS
    说ä»Ģä¹Ī
    0.09
    æķĻä½ł
    0.08
    _DECLARE
    0.08
    åįĩåįİ
    0.08
    GetMethod
    0.08
     sĩ
    0.08
    åĬ¿å¤´
    0.08
    åħŃåIJĪ
    0.08
    åĬ¨åijĺ
    0.08
    dden
    0.08
    Activations Density 0.017%

    No Known Activations