© 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. 1474
    Prev
    Next
    INDEX
    Explanations

    books and cookbooks

    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
    éħĬ
    -0.10
    åı£ä¸Ń
    -0.09
     epic
    -0.08
    书åºĹ
    -0.08
    å¥ĩçī¹
    -0.08
    èĭ±çī¹
    -0.08
     tin
    -0.08
    ôn
    -0.08
    /is
    -0.08
    asser
    -0.08
    POSITIVE LOGITS
    yard
    0.11
    éŨåīį
    0.10
    .toJSON
    0.10
    Mari
    0.09
     ÐľÐ°ÑĢи
    0.09
    elling
    0.09
    ãĥĹ
    0.08
    .opens
    0.08
    riers
    0.08
    ç«ĭæ¡Ī
    0.08
    Activations Density 0.019%

    No Known Activations