© 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. 22691
    Prev
    Next
    INDEX
    Explanations

    gene expression

    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
    渥
    -0.10
    æ²±
    -0.09
    tie
    -0.09
    oola
    -0.09
    åıĺåİĭ
    -0.09
    æĮĩæłĩ
    -0.09
    åijĺ
    -0.09
    bon
    -0.09
    /qt
    -0.09
    溪
    -0.09
    POSITIVE LOGITS
     prof
    0.09
     throughout
    0.09
    Spinner
    0.09
    atem
    0.08
     Million
    0.08
    é£ı
    0.08
     prior
    0.08
    inue
    0.08
    çıĬçijļ
    0.08
    èıľ
    0.08
    Activations Density 0.452%

    No Known Activations