© 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. 18318
    Prev
    Next
    INDEX
    Explanations

    opioid drugs and their use

    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
    æĢ¦
    -0.10
    ?url
    -0.08
    é¢ĦåħĪ
    -0.08
    å½·
    -0.08
    æĪIJéķ¿ä¸º
    -0.08
    ile
    -0.08
    èŀį
    -0.08
     lineno
    -0.08
    iles
    -0.08
    ETS
    -0.08
    POSITIVE LOGITS
     opioid
    0.12
     pain
    0.11
    çĸ¼çĹĽ
    0.11
    /AP
    0.10
    ç½Ĥ
    0.10
     opioids
    0.09
    çĹĽ
    0.09
    èĩĬ
    0.09
    itus
    0.09
    èı©
    0.09
    Activations Density 0.149%

    No Known Activations