© 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. 39904
    Prev
    Next
    INDEX
    Explanations

    phone numbers and prices

    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
    lop
    -0.08
    _do
    -0.08
    sar
    -0.08
     Niger
    -0.07
     wondering
    -0.07
    èĢĥéªĮ
    -0.07
    纷
    -0.07
    uye
    -0.07
    sic
    -0.07
    mland
    -0.07
    POSITIVE LOGITS
    .tel
    0.10
    åħĪæĬĬ
    0.10
    opi
    0.10
    ä»»ä½ķå½¢å¼ı
    0.10
     Humph
    0.10
    åı·çłģ
    0.09
    ä½ľèĢħæľ¬äºº
    0.09
    éĺ¡
    0.09
    æľīå¤ļ
    0.09
    å½ĵåľ°çļĦ
    0.09
    Activations Density 0.012%

    No Known Activations