© 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. 19903
    Prev
    Next
    INDEX
    Explanations

    honoring recipients

    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
    /small
    -0.10
    è¢Ĥ
    -0.09
    upe
    -0.09
    gun
    -0.09
    ĭ
    -0.09
    庵
    -0.09
    afort
    -0.08
    ingle
    -0.08
    àºŃ
    -0.08
    ä¼Ĺ
    -0.08
    POSITIVE LOGITS
    许
    0.10
    зÑĥ
    0.10
     oma
    0.10
     subpo
    0.09
    ymous
    0.09
     traditions
    0.09
    zá
    0.09
    ably
    0.09
    ìłľ
    0.09
    碼
    0.09
    Activations Density 0.012%

    No Known Activations