© 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. 17914
    Prev
    Next
    INDEX
    Explanations

    word endings (est, eter, ict, woo, ird, ec)

    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
    ials
    -0.09
    udies
    -0.09
    ters
    -0.08
    -thirds
    -0.08
    adin
    -0.08
    -know
    -0.08
    æľ¨èĢ³
    -0.08
    à¸Ļาม
    -0.08
    ãģĤãģ£ãģ¦
    -0.08
    涮
    -0.08
    POSITIVE LOGITS
     noqa
    0.10
    д
    0.08
    uration
    0.08
    presso
    0.08
    iled
    0.08
    ại
    0.08
    olute
    0.08
     tù
    0.08
    icked
    0.08
    eries
    0.07
    Activations Density 2.446%

    No Known Activations