© 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. 1642
    Prev
    Next
    INDEX
    Explanations

    do what

    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
    è·¨
    -0.23
     nested
    -0.22
    æĽ¿
    -0.22
    ä»ĭåħ¥
    -0.22
    åħħçĶµ
    -0.22
    éĿŀ常好
    -0.22
     nest
    -0.22
    èĢĹ
    -0.21
     advance
    -0.21
    -intensive
    -0.21
    POSITIVE LOGITS
     conscience
    0.31
     instincts
    0.31
    æ½®æµģ
    0.28
     impulses
    0.28
    è¡Įäºĭ
    0.27
     dictated
    0.27
    åİŁåĪĻ
    0.27
     instinct
    0.25
     heed
    0.25
    æĦıæĦ¿
    0.25
    Activations Density 0.037%

    No Known Activations