© 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. 22963
    Prev
    Next
    INDEX
    Explanations

    Ella Fitzgerald

    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
    æĢ§å¼º
    -0.10
    åīįæīĢ
    -0.09
    izador
    -0.09
    足
    -0.09
    ombat
    -0.09
    ntl
    -0.08
     epis
    -0.08
    foot
    -0.08
    èľ·
    -0.08
    GMT
    -0.08
    POSITIVE LOGITS
    æ·Ģ
    0.10
    ä¼Ĺ
    0.09
    åĶ±
    0.09
    å¾Īå·®
    0.09
    ä¿Ŀ湿
    0.09
    人çĶŁçļĦ
    0.09
    åģľæĶ¾
    0.09
    ience
    0.08
    æĹłç¼ĺ
    0.08
    士
    0.08
    Activations Density 0.002%

    No Known Activations