© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    record when, Social Media

    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
    éĢĢä¼ij
    -0.27
    è°¬
    -0.24
    osl
    -0.23
    --[
    -0.23
    .unwrap
    -0.22
    ffen
    -0.21
    责任ç¼ĸè¾ij
    -0.21
     retiring
    -0.21
    çĽijçĿ£ç®¡çIJĨ
    -0.21
     fluids
    -0.21
    POSITIVE LOGITS
     submission
    0.32
    积累
    0.30
    isma
    0.30
    è¯ģæĺİ
    0.29
    çĶ³è¯·
    0.29
    ä¸ĬæĬ¥
    0.29
    ·»
    0.29
    è¿°èģĮ
    0.28
    æıIJ交
    0.28
    åĬłåĪĨ
    0.28
    Activations Density 0.236%

    No Known Activations