© 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. 2967
    Prev
    Next
    INDEX
    Explanations

    opioid, addictive, drug, abused, overdose

    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
     splash
    -0.30
     Splash
    -0.26
     settling
    -0.25
    startup
    -0.24
    æ¦ħ
    -0.24
     SplashScreen
    -0.23
    æ°´è´¨
    -0.23
     reunion
    -0.23
    æİī
    -0.23
     supporter
    -0.23
    POSITIVE LOGITS
    çĶ¨éĩı
    0.40
    çĶ¨èį¯
    0.38
    å¤Ħæĸ¹
    0.37
     opioid
    0.37
    èį¯çī©
    0.36
     opioids
    0.36
     drug
    0.35
    èį¯åºĹ
    0.34
    æ¯Ĵåĵģ
    0.34
     heroin
    0.34
    Activations Density 0.043%

    No Known Activations