© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37499
    Prev
    Next
    INDEX
    Explanations

    trademarks

    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
    combe
    -0.09
    omanip
    -0.09
    hood
    -0.09
    lé
    -0.09
     Ricardo
    -0.08
    åħļæĢ»
    -0.08
     dÃłng
    -0.08
    brook
    -0.08
    äºĮèĥİ
    -0.08
    лиз
    -0.08
    POSITIVE LOGITS
    eter
    0.10
    elijk
    0.09
    gable
    0.09
    amp
    0.09
    ed
    0.08
    à¸Ļาย
    0.08
    yla
    0.08
    eting
    0.08
    esch
    0.08
    è°ij
    0.08
    Activations Density 0.003%

    No Known Activations