© 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. 18021
    Prev
    Next
    INDEX
    Explanations

    Unimatrix Zero, time turner, cutie mark, Yithians, Tribbles

    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
    æĸ°åįİç½ij
    -0.09
    ẽ
    -0.08
    æ´¥
    -0.08
    AtPath
    -0.08
    沿
    -0.08
    è§Ī
    -0.08
    ä¸įå¼Ģ
    -0.08
    æĺ¯ä»İ
    -0.08
    åı£å¾Ħ
    -0.08
    èIJ½å®ŀ
    -0.07
    POSITIVE LOGITS
    à¹ģà¸Ĺ
    0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    0.09
    éģ¥æݧ
    0.08
    udget
    0.08
    пед
    0.08
     Mime
    0.08
    åıĤ
    0.08
    plusplus
    0.08
    çħ§
    0.08
    aphael
    0.08
    Activations Density 0.060%

    No Known Activations