© 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. 3268
    Prev
    Next
    INDEX
    Explanations

    relief pitcher or substitute

    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
    ç¾½
    -0.25
    asted
    -0.23
    Bright
    -0.22
    Subscriber
    -0.21
     underground
    -0.21
    ChangeListener
    -0.21
     crem
    -0.20
     uninsured
    -0.20
    eded
    -0.20
    Breadcrumb
    -0.20
    POSITIVE LOGITS
    é«ĺæīĭ
    0.25
    æĢª
    0.24
    chio
    0.23
    åºĸ
    0.22
     kin
    0.22
    主ä¹īæĢĿæĥ³
    0.22
    æĺ¯éŁ©åĽ½
    0.22
    æIJĵ
    0.22
    åİĭåĬĽ
    0.22
    æİ·
    0.21
    Activations Density 0.001%

    No Known Activations