© 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. 54370
    Prev
    Next
    INDEX
    Explanations

    folic acid, case-control, Galera cluster

    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
     há»ĵi
    -0.10
    æĴ¼
    -0.09
    å¢ĥå¤ĸ
    -0.09
    ECT
    -0.09
    çİ°çĬ¶
    -0.09
    æ¦ľ
    -0.09
    ä»·
    -0.09
    åŀŃ
    -0.09
    åĽ½åĨħå¸Ĥåľº
    -0.09
    æİ¢
    -0.08
    POSITIVE LOGITS
    cÃŃ
    0.09
    inals
    0.08
    unas
    0.08
     Gavin
    0.07
    isson
    0.07
    aul
    0.07
    Unavailable
    0.07
    ç²¾åĵģ
    0.07
    inal
    0.07
    yled
    0.07
    Activations Density 0.003%

    No Known Activations