© 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. 32011
    Prev
    Next
    INDEX
    Explanations

    breeze, zephyr, bris

    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
    ity
    -0.10
    sson
    -0.10
    /IP
    -0.09
    ãĤĪãģĨãģª
    -0.09
    ondo
    -0.09
    rous
    -0.08
    aceous
    -0.08
    ization
    -0.08
    ish
    -0.08
    æĶ»åĿļ
    -0.08
    POSITIVE LOGITS
    æĮĽ
    0.10
    æľīæĦı
    0.10
    emente
    0.09
    unner
    0.09
    mare
    0.09
    æĢ¡
    0.09
    atics
    0.08
    ingly
    0.08
    bare
    0.08
    eners
    0.08
    Activations Density 0.003%

    No Known Activations