© 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. 1775
    Prev
    Next
    INDEX
    Explanations

    illegal drug production

    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
     traveler
    -0.27
     ambassadors
    -0.25
    Interaction
    -0.24
    客æµģ
    -0.24
     commuters
    -0.24
    Rails
    -0.23
     Interaction
    -0.23
     travelers
    -0.23
     traveller
    -0.23
    漫æŃ¥
    -0.23
    POSITIVE LOGITS
    ä½ľåĿĬ
    0.36
     clandest
    0.35
    éļIJèĶ½
    0.33
    éĿŀæ³ķ
    0.29
     illegal
    0.29
     hidden
    0.29
     disguised
    0.28
     makeshift
    0.28
    æıIJçĤ¼
    0.27
    éħ¿
    0.27
    Activations Density 0.008%

    No Known Activations