© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2862
    Prev
    Next
    INDEX
    Explanations

    English language requirements

    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
    IMPLEMENT
    -0.28
    (_,
    -0.26
    .addProperty
    -0.26
    PROP
    -0.23
    åŁĮ
    -0.23
    æĢĿç´¢
    -0.23
    å¬Ĺ
    -0.23
    å°ıåºĹ
    -0.23
    éģįåıĬ
    -0.23
    éĩįå¡ij
    -0.22
    POSITIVE LOGITS
     qualifying
    0.29
    åIJĪæł¼
    0.28
     sufficient
    0.28
     qualification
    0.27
    åŃ¦è´¹
    0.27
     guarantee
    0.27
     compr
    0.27
    éĽħæĢĿ
    0.26
     certification
    0.26
     degree
    0.26
    Activations Density 0.005%

    No Known Activations