© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60856
    Prev
    Next
    INDEX
    Explanations

    the before specific nouns

    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
    èį¯ä¸ļ
    -0.10
    æľīèĩªå·±çļĦ
    -0.09
    寿
    -0.09
    æ¡¢
    -0.09
    å¯Ħ
    -0.09
    æľī两个
    -0.09
    æ¸ł
    -0.09
    å¯Ĩ
    -0.09
    æīĥ
    -0.09
    .internet
    -0.09
    POSITIVE LOGITS
     reason
    0.11
    è¿Ľå±ķæĥħåĨµ
    0.10
    缸åħ³ä¿¡æģ¯
    0.10
    OLS
    0.09
     details
    0.09
    è·¯å¾Ħ
    0.08
    æľĢæĸ°çļĦ
    0.08
     updated
    0.08
    hum
    0.08
    hil
    0.08
    Activations Density 0.239%

    No Known Activations