© 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. 3245
    Prev
    Next
    INDEX
    Explanations

    touching against

    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
    辫
    -0.27
    bidden
    -0.25
    ä¸įæĺİ
    -0.23
    bol
    -0.23
    èİĺ
    -0.23
    寻常
    -0.22
    æ»Ķ
    -0.22
    漩
    -0.22
    å¸ľ
    -0.22
    大çģ«
    -0.22
    POSITIVE LOGITS
     lean
    0.31
     leaned
    0.29
    å¢Ļå£ģ
    0.26
    éĿłçĿĢ
    0.26
    .wx
    0.26
    Lean
    0.26
    åĢļ
    0.25
     leaning
    0.24
     leans
    0.23
    INGTON
    0.23
    Activations Density 0.016%

    No Known Activations