© 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. 53711
    Prev
    Next
    INDEX
    Explanations

    easy, easier, ease

    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
    /tiny
    -0.09
    çݯå¢ĥä¸Ń
    -0.09
    fulness
    -0.09
    æĪIJ绩åįķ
    -0.09
    ÑĤен
    -0.09
    ìį¨
    -0.09
    æĺĮ
    -0.09
    æĪĺæľ¯
    -0.09
    å·¥
    -0.08
    积èĵĦ
    -0.08
    POSITIVE LOGITS
    å¾Īç®Ģåįķ
    0.15
    ç®Ģåįķ
    0.15
     easy
    0.15
    åıªéľĢ
    0.14
    ç®ĢåįķçļĦ
    0.13
     easier
    0.13
    ç°¡åįĺ
    0.12
     ease
    0.12
    æ¯Ķè¾ĥç®Ģåįķ
    0.12
    åıªéľĢè¦ģ
    0.12
    Activations Density 0.098%

    No Known Activations