© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48594
    Prev
    Next
    INDEX
    Explanations

    heroin use and overdose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    串
    -0.09
    ç»İ
    -0.08
    è®
    -0.08
    ä¹ĭåĬĽ
    -0.08
    oon
    -0.08
    鱼类
    -0.08
    ä¹ĭä½ľ
    -0.08
     Vance
    -0.08
    好äºĭ
    -0.08
    ä¸Ģéģĵ
    -0.08
    POSITIVE LOGITS
    ç½ij讯
    0.09
    /ros
    0.09
    æĻ¯å¾·éķĩ
    0.08
    OutOfBounds
    0.08
    der
    0.08
    åIJ¸æ¯Ĵ
    0.08
    æĮĩæľĽ
    0.08
    æ¡ĪåŃIJ
    0.08
    çĹķ迹
    0.08
    éħ´
    0.08
    Activations Density 0.054%

    No Known Activations