© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15883
    Prev
    Next
    INDEX
    Explanations

    stimulant medication effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    entai
    -0.21
    çݯå¢ĥåį«çĶŁ
    -0.19
     Suns
    -0.19
    åįłåľ°
    -0.19
    дон
    -0.18
    ׼×ķ׾
    -0.18
    aries
    -0.18
    uty
    -0.18
    ssf
    -0.18
    -opacity
    -0.18
    POSITIVE LOGITS
    ç²īæľ«
    0.20
    åĬłå¼ºå¯¹
    0.18
    رÙĬØŃ
    0.18
     phê
    0.18
    è¶Ĭé«ĺ
    0.17
    Tam
    0.17
    ä¸Ĭ课
    0.17
    èµĦæľ¬ä¸»ä¹ī
    0.17
    athan
    0.17
    æļĸå¿ĥ
    0.17
    Activations Density 0.005%

    No Known Activations