© 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. 56541
    Prev
    Next
    INDEX
    Explanations

    mill, Bubble, Henry, kick, ish

    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
     ÐľÐ¾
    -0.09
    å»īä»·
    -0.08
    æĪijçļĦå¿ĥ
    -0.08
    ç»İ
    -0.08
     fingerprints
    -0.08
    æĪijæīį
    -0.08
    éľ¹
    -0.08
    ä¸įåıĺ
    -0.08
     Advent
    -0.08
    losure
    -0.08
    POSITIVE LOGITS
    ish
    0.10
    amespace
    0.10
    ishly
    0.10
    壮
    0.09
    ÃŃstica
    0.09
    å¼ı
    0.09
    stype
    0.09
    iloc
    0.09
    æ¿ij
    0.09
     Shirley
    0.08
    Activations Density 0.003%

    No Known Activations