© 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. 22975
    Prev
    Next
    INDEX
    Explanations

    words ending in er/or/ifier/cks/ler

    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
    ÑıÑĤÑĮ
    -0.09
    å¼¥
    -0.08
    馥
    -0.08
    æµĭè¯Ħ
    -0.08
    attro
    -0.08
    ç°ĭ
    -0.08
    æĹºçĽĽ
    -0.08
     noqa
    -0.08
    æĹłè¾ľ
    -0.08
    king
    -0.08
    POSITIVE LOGITS
    å±IJ
    0.11
    ovsky
    0.09
    çļĦæĦŁåıĹ
    0.09
    thro
    0.09
     Bengal
    0.09
    edom
    0.09
    -ending
    0.09
    å·¥åºı
    0.08
    å¿ĺäºĨ
    0.08
    ade
    0.08
    Activations Density 0.002%

    No Known Activations