© 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. 579
    Prev
    Next
    INDEX
    Explanations

    obesity, kg, thresholds, normal

    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
     Steam
    -0.26
     hybrid
    -0.26
     Hybrid
    -0.25
    ç»ıèIJ¥æ¨¡å¼ı
    -0.25
     Dual
    -0.24
    éĩĮç¨ĭ
    -0.24
    çļĦæĪIJéķ¿
    -0.22
    ampp
    -0.22
     dual
    -0.22
    æľºçĶµ
    -0.21
    POSITIVE LOGITS
    åį±å®³
    0.32
    è¿ĩ度
    0.25
    riteria
    0.25
    åį±éĻ©
    0.24
     thresholds
    0.23
    osity
    0.23
    æľī害
    0.23
    danger
    0.23
    çĹĩçĬ¶
    0.23
    è¿ĩé«ĺ
    0.23
    Activations Density 0.059%

    No Known Activations