© 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. 53900
    Prev
    Next
    INDEX
    Explanations

    "be that"

    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
    伺
    -0.10
     cand
    -0.09
    羣çļĦ
    -0.08
    quan
    -0.08
    说ä¸įå®ļ
    -0.08
    è¦ĨçĽĸçİĩ
    -0.08
    æ¼±
    -0.08
    çĶ±æѤ
    -0.08
     wÅĤ
    -0.08
    çīĪæĿĥæīĢæľī
    -0.08
    POSITIVE LOGITS
     rằng
    0.14
     bahwa
    0.13
     hogy
    0.10
     Ø£ÙĨÙĩ
    0.09
    skirts
    0.09
    или
    0.09
    orer
    0.09
     that
    0.09
    说æĪij
    0.09
     dass
    0.08
    Activations Density 0.046%

    No Known Activations