© 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. 3386
    Prev
    Next
    INDEX
    Explanations

    pre-assembled software installed

    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
    onia
    -0.24
    /var
    -0.24
    oning
    -0.23
     republic
    -0.22
     super
    -0.22
    å¼Ģ头
    -0.21
    è¿ĺ
    -0.21
    api
    -0.21
    AMES
    -0.21
    aida
    -0.21
    POSITIVE LOGITS
     CLICK
    0.23
     DVDs
    0.23
    	ptr
    0.22
    .yy
    0.22
    PFN
    0.21
    ãģĦãģ¾ãģĻ
    0.21
    elda
    0.21
    å®ĮåĸĦçļĦ
    0.21
    psc
    0.21
    OUR
    0.21
    Activations Density 0.054%

    No Known Activations