© 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. 3079
    Prev
    Next
    INDEX
    Explanations

    x86_64, i686, amd64 architectures

    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
    DBObject
    -0.26
    rances
    -0.24
    adays
    -0.23
    iação
    -0.23
    -related
    -0.23
    hiba
    -0.21
    iales
    -0.21
    MenuItem
    -0.21
    ItemImage
    -0.21
    Edited
    -0.21
    POSITIVE LOGITS
    åĨħåŃĺ
    0.28
    çīĪ
    0.26
    åºŃ
    0.26
     desktop
    0.24
    嶷
    0.24
    缸
    0.23
    æľ¬åľ°
    0.23
    æ¡ĮéĿ¢
    0.23
    éĺ²æ°´
    0.22
    大å¤ļæĺ¯
    0.22
    Activations Density 0.062%

    No Known Activations