© 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. 61029
    Prev
    Next
    INDEX
    Explanations

    Italian words ending: -etti, -etti, -etti

    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
    çıŀ
    -0.10
    ús
    -0.08
    blas
    -0.08
    ulen
    -0.08
    hea
    -0.08
    ucas
    -0.08
    æ¬
    -0.08
    ene
    -0.08
     sorter
    -0.08
    åħ¬åŃIJ
    -0.07
    POSITIVE LOGITS
    æ©IJ
    0.10
    京津åĨĢ
    0.10
    RESH
    0.09
    æľ¬æĬ¥
    0.09
    æł¸æ¡ĥ
    0.09
    æľºä½ĵ
    0.09
    /security
    0.09
     плоÑħо
    0.09
    IRS
    0.09
    vern
    0.08
    Activations Density 0.009%

    No Known Activations