© 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. 3349
    Prev
    Next
    INDEX
    Explanations

    freshly processed or prepared

    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
    и
    -0.25
    abler
    -0.22
    åį³ä½¿æĺ¯
    -0.21
     Commonwealth
    -0.21
    æĦıå¢ĥ
    -0.21
    責任
    -0.20
    åĴĮæĶ¯æĮģ
    -0.20
    åħ¨ç¤¾ä¼ļ
    -0.20
    责任
    -0.20
    åĮº
    -0.20
    POSITIVE LOGITS
     mint
    0.28
     digit
    0.24
    combe
    0.24
    stral
    0.23
    -made
    0.23
    aneously
    0.22
    á»ģn
    0.22
    棵æłij
    0.22
    tı
    0.21
     disc
    0.21
    Activations Density 0.002%

    No Known Activations