© 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. 2912
    Prev
    Next
    INDEX
    Explanations

    later or thereafter

    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
     nowhere
    -0.23
    ä¸ĢåĪĻ
    -0.22
     pep
    -0.22
    пÑĢÑı
    -0.21
     redd
    -0.21
     traps
    -0.21
     rests
    -0.21
    é¤ĺ
    -0.20
    è¿Ļä¸Ģ天
    -0.20
    ä¸įåħ·å¤ĩ
    -0.20
    POSITIVE LOGITS
    åIJİæĿ¥
    0.49
     later
    0.43
    later
    0.35
    Later
    0.35
    å¾Įä¾Ĩ
    0.35
     thereafter
    0.34
     Later
    0.34
    æ¸IJæ¸IJ
    0.33
    åIJİæľŁ
    0.33
    éĢIJæ¸IJ
    0.32
    Activations Density 0.190%

    No Known Activations