© 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. 62694
    Prev
    Next
    INDEX
    Explanations

    marijuana possession and drug offenses

    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
    æ¯ĽåŃĶ
    -0.10
    æ·ĺ
    -0.09
     trillion
    -0.09
    oux
    -0.08
    ä¹Į
    -0.08
    æµ´
    -0.08
    íĽĪ
    -0.08
    ship
    -0.08
    .nz
    -0.08
    ting
    -0.07
    POSITIVE LOGITS
    è¯¥æł¡
    0.09
    称ä¹ĭ
    0.09
    ç²ī
    0.08
    é«ĺæķĪçļĦ
    0.08
    ä½ĵçİ°äºĨ
    0.08
    ãģĭãģ£ãģŁãģ§ãģĻ
    0.08
    avier
    0.08
    æŀ
    0.08
    æīĩ
    0.08
    æºĸåĤĻ
    0.08
    Activations Density 0.029%

    No Known Activations