© 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. 17137
    Prev
    Next
    INDEX
    Explanations

    html doctype

    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
     лиÑĨ
    -0.09
    éĨī
    -0.09
    adem
    -0.09
     деле
    -0.09
    æĴĴ
    -0.09
    åĢį
    -0.09
    综åIJĪæĢ§
    -0.09
    æģĭæĥħ
    -0.09
    lez
    -0.08
    หà¸Ļ
    -0.08
    POSITIVE LOGITS
    è°´
    0.09
    æĶ¾æīĭ
    0.08
    iland
    0.08
    æŃī
    0.08
    etre
    0.08
     Frag
    0.08
    ÙĨØ©
    0.08
    osci
    0.08
    epam
    0.08
    endencies
    0.07
    Activations Density 0.029%

    No Known Activations