© 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. 2667
    Prev
    Next
    INDEX
    Explanations

    screening procedures

    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
    æĪIJéķ¿
    -0.28
    ä¸ŃæľŁ
    -0.27
    åĪĽä½ľ
    -0.26
    growth
    -0.26
     growth
    -0.26
     Invest
    -0.26
    åŃķèĤ²
    -0.26
     Sabb
    -0.26
     Growth
    -0.25
     inheritance
    -0.25
    POSITIVE LOGITS
    å®īæ£Ģ
    0.65
    æŁ¥éªĮ
    0.39
    å®īåħ¨
    0.38
    æī§åĭ¤
    0.38
    åĩºåħ¥å¢ĥ
    0.36
    æ°ijèĪª
    0.36
    æĬ½æŁ¥
    0.36
    çŃĽæŁ¥
    0.36
    .gov
    0.35
     passengers
    0.35
    Activations Density 0.041%

    No Known Activations