© 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. 33032
    Prev
    Next
    INDEX
    Explanations

    cod, codified, codomain, codename, codon

    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
    ably
    -0.09
    sic
    -0.09
    ful
    -0.09
    åIJģ
    -0.09
    fully
    -0.09
    à¹ĩà¸Ļ
    -0.08
    leton
    -0.08
    anos
    -0.08
    finder
    -0.08
    holding
    -0.08
    POSITIVE LOGITS
    rate
    0.11
    balls
    0.10
    rende
    0.10
     обÑĢазом
    0.10
    yssey
    0.10
    ALLY
    0.09
    æĹģ
    0.09
    ÑĮÑİ
    0.09
    é©¿
    0.09
    irth
    0.09
    Activations Density 0.018%

    No Known Activations