© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3169
    Prev
    Next
    INDEX
    Explanations

    words preceding proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     nothing
    -0.27
    nothing
    -0.26
    æ´¼
    -0.23
    è¯Ń
    -0.23
     nada
    -0.23
    Nothing
    -0.22
    èŀįåĮĸ
    -0.21
    æ°°
    -0.21
    ä¿¡æģ¯
    -0.21
    -gnu
    -0.20
    POSITIVE LOGITS
     both
    0.26
    alach
    0.24
    avig
    0.24
    åIJĦ家
    0.23
     обо
    0.23
    ...]↵↵
    0.23
    æĪij家
    0.21
    LEM
    0.21
    ä¸ĩ家
    0.21
    åIJĦ
    0.21
    Activations Density 0.368%

    No Known Activations