© 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. 2675
    Prev
    Next
    INDEX
    Explanations

    comparisons of different

    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
    åıĮéĩį
    -0.26
    åĿļåĽº
    -0.26
    å¿ħè¦ģçļĦ
    -0.26
     powerful
    -0.25
    ama
    -0.24
    æĹłåĬ©
    -0.23
    bek
    -0.22
    aut
    -0.21
    解éĻ¤
    -0.21
     Gujar
    -0.21
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.67
     different
    0.66
    çļĦä¸įåIJĮ
    0.65
    different
    0.64
    ä¸įåIJĮ
    0.63
     differing
    0.63
     differently
    0.59
    Different
    0.58
     ÑĢазнÑĭÑħ
    0.57
    çļĦåĮºåĪ«
    0.56
    Activations Density 0.636%

    No Known Activations