© 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. 3024
    Prev
    Next
    INDEX
    Explanations

    solo exhibitions

    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
     toll
    -0.25
    Football
    -0.24
    football
    -0.24
    омн
    -0.23
    æĺī
    -0.23
     UNESCO
    -0.23
     века
    -0.23
    criptor
    -0.23
    çĶ¨æĿ¥
    -0.23
     FIFA
    -0.23
    POSITIVE LOGITS
    é¦ĸ次
    0.31
     debut
    0.28
    é¦ĸè½®
    0.26
    å±ķåĩº
    0.26
    ä¸Ńæĸ°
    0.25
    ãĤĴè¿İ
    0.25
    çĶŁäº§åŁºåľ°
    0.24
    第äºĮ次
    0.23
     début
    0.23
    his
    0.23
    Activations Density 0.019%

    No Known Activations