© 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. 2671
    Prev
    Next
    INDEX
    Explanations

    later life stages

    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
     refreshing
    -0.26
    æ¯ı次
    -0.26
     stale
    -0.25
    æ¯ıæĹ¥
    -0.25
    imator
    -0.24
    èµİåĽŀ
    -0.24
     bait
    -0.24
    è°Ħ
    -0.24
    æ¯ı次éĥ½
    -0.24
    é¢ijç¹ģ
    -0.23
    POSITIVE LOGITS
     later
    0.50
     adulthood
    0.49
    later
    0.48
     lifelong
    0.45
    Later
    0.44
    ç»Ī身
    0.44
    åѦä¸ļ
    0.44
     adolescence
    0.41
    éķ¿å¤§
    0.40
    ç»ĪçĶŁ
    0.40
    Activations Density 0.113%

    No Known Activations