© 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. 36408
    Prev
    Next
    INDEX
    Explanations

    college education

    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
    èıģ
    -0.10
    æ´Ľ
    -0.09
     lob
    -0.09
    ymous
    -0.09
     Ñĥдален
    -0.09
    unn
    -0.09
    éķĤ
    -0.08
    èIJ½åľ¨
    -0.08
     Lob
    -0.08
    ä¾Ľç»Ļ侧
    -0.08
    POSITIVE LOGITS
    积åĪĨ
    0.10
    家åºŃ
    0.10
    æĻļé¥Ń
    0.09
    åħ¨å®¶
    0.09
    çļĦ家åºŃ
    0.09
    iglia
    0.09
    çĿ¡åīį
    0.09
    çģĮ
    0.08
    å°Ĭ
    0.08
    æĶĴ
    0.08
    Activations Density 0.080%

    No Known Activations