© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6780
    Prev
    Next
    INDEX
    Explanations

    drug use and related issues

    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
    å¤ĸèµĦ
    -0.09
    é¹³
    -0.09
    vat
    -0.09
    anken
    -0.09
    åIJĮæľŁ
    -0.09
    igsaw
    -0.08
    æĥķ
    -0.08
    轶
    -0.08
     Nel
    -0.08
    西äºļ
    -0.08
    POSITIVE LOGITS
    åIJ¸æ¯Ĵ
    0.12
    æ¯Ĵåĵģ
    0.12
    æĪĴ
    0.11
     cocaine
    0.10
    çĺ¾
    0.10
    6
    0.09
    å°ĸ
    0.09
    ä¸Ĭç½ij
    0.09
    ç¦ģæ¯Ĵ
    0.09
    ä¹°åįĸ
    0.09
    Activations Density 0.175%

    No Known Activations