© 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. 1018
    Prev
    Next
    INDEX
    Explanations

    free software

    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
     ...↵
    -0.24
    ï½ľ
    -0.23
    å²±
    -0.23
    tech
    -0.22
    æ·Ł
    -0.22
    .dev
    -0.21
     podcast
    -0.21
    ç®ĢåĮĸ
    -0.21
     tech
    -0.21
    slice
    -0.21
    POSITIVE LOGITS
    éĿŀ常çļĦ
    0.29
    éĥ¨ä»½
    0.28
    éĿŀ常好çļĦ
    0.26
    Intialized
    0.26
    æħ¢æħ¢çļĦ
    0.26
    ä¸įåģľçļĦ
    0.25
     greatly
    0.24
    沦
    0.24
    ä»İæĿ¥æ²¡æľī
    0.24
     absolutely
    0.24
    Activations Density 0.116%

    No Known Activations