© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7665
    Prev
    Next
    INDEX
    Explanations

    side, position, aboard

    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
    é«Ģ
    -0.09
    ible
    -0.09
    _SAN
    -0.09
    羣åģĩ
    -0.09
     Learned
    -0.09
    å¼Ģåıij建设
    -0.09
    èĥĦ
    -0.09
    çªł
    -0.08
    icle
    -0.08
    å°¤
    -0.08
    POSITIVE LOGITS
     favor
    0.12
    ç«Ļåľ¨
    0.11
    æĶ¯æĮģ
    0.11
    人åĬĽ
    0.10
    åĤį
    0.10
     favour
    0.10
    æĹģ
    0.09
    awan
    0.09
    favor
    0.09
    说æľį
    0.09
    Activations Density 0.047%

    No Known Activations