© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 763
    Prev
    Next
    INDEX
    Explanations

    names like Marie, Singh, Aaron, Patrick

    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
    éģĩä¸Ĭ
    -0.24
     COPYING
    -0.23
     Hispanics
    -0.23
    èĿĩ
    -0.23
    æīĵ交
    -0.23
    å°ıäºĭ
    -0.23
    迤
    -0.22
    orno
    -0.22
    åı£æ°Ķ
    -0.21
    ORED
    -0.21
    POSITIVE LOGITS
    ç¦ħ
    0.29
     retired
    0.27
    åľ¨ä¸Ĭæµ·
    0.27
    çļĦ带é¢Ĩä¸ĭ
    0.26
    SSI
    0.26
    带é¢Ĩ
    0.25
     ordained
    0.24
     Nom
    0.24
     rising
    0.24
    joy
    0.23
    Activations Density 0.033%

    No Known Activations