© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    Scott Gordon

    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
    çĪ¨
    -0.29
    ppy
    -0.24
     onto
    -0.24
    çļĦ妻åŃIJ
    -0.23
    xfb
    -0.22
    pped
    -0.22
    æīŃæĽ²
    -0.22
    Dragging
    -0.21
    好çľĭ
    -0.21
    Ñĩив
    -0.21
    POSITIVE LOGITS
     Desert
    0.25
    驾
    0.24
     desert
    0.23
    åĨ¢
    0.23
    åĽŃ
    0.23
     theories
    0.22
    èī¯å¿ĥ
    0.22
    驹
    0.22
     quil
    0.22
     reasonable
    0.22
    Activations Density 0.004%

    No Known Activations