© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21479
    Prev
    Next
    INDEX
    Explanations

    News and reports

    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
    缺å¸Ń
    -0.09
    令
    -0.08
    à¸ķำ
    -0.08
    ocz
    -0.08
    éĤĪ
    -0.08
    çīĿ
    -0.08
     Klo
    -0.08
    meno
    -0.08
    lique
    -0.07
    Hist
    -0.07
    POSITIVE LOGITS
    éľīç´ł
    0.09
    usted
    0.09
    å¦ĤæĦı
    0.09
     Rug
    0.09
    alus
    0.09
    ãģĹãĤĩãģĨ
    0.09
    缣
    0.09
    èłķ
    0.09
    ulus
    0.08
    æľīæĦı
    0.08
    Activations Density 0.003%

    No Known Activations