© 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. 39172
    Prev
    Next
    INDEX
    Explanations

    drug and substance abuse

    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
    _initialized
    -0.09
    èĢĥè¯Ħ
    -0.09
    ê¹ĥ
    -0.09
    端åįĪ
    -0.09
    lok
    -0.09
    çĦ¯
    -0.09
    ä¾Ľæļĸ
    -0.09
    èĿĹ
    -0.09
    éļIJéļIJ
    -0.08
    æĶ¶åĽŀ
    -0.08
    POSITIVE LOGITS
    èį¯çī©
    0.14
     drugs
    0.13
    èį¯
    0.12
    èį¯åĵģ
    0.12
    æ¿Ģç´ł
    0.11
    èĹ¥
    0.11
    æľįçĶ¨
    0.11
    å¼Ģåħ·
    0.11
     drug
    0.10
     prescription
    0.10
    Activations Density 0.152%

    No Known Activations