© 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. 3093
    Prev
    Next
    INDEX
    Explanations

    of Historic Places

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .TryParse
    -0.24
    Bonus
    -0.24
    ücü
    -0.22
    ç²Ĺ
    -0.21
     superiority
    -0.21
     ///<
    -0.21
     subclass
    -0.21
    ANTA
    -0.21
    çŃĨ
    -0.20
    hiba
    -0.20
    POSITIVE LOGITS
    ryn
    0.24
     freaking
    0.23
    åľ¨åĵªéĩĮ
    0.23
     famously
    0.23
     Windsor
    0.23
    /from
    0.23
     Whatever
    0.23
    ä¹Łå°±æĺ¯è¯´
    0.22
     âĪ
    0.22
    说ä»Ģä¹Ī
    0.22
    Activations Density 0.109%

    No Known Activations