© 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. 49003
    Prev
    Next
    INDEX
    Explanations

    potent drug or agent

    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
    sWith
    -0.10
    lar
    -0.09
    itch
    -0.09
    ses
    -0.09
    shire
    -0.08
    habi
    -0.08
    ITCH
    -0.08
    sp
    -0.08
    çľ¾
    -0.08
    諸
    -0.08
    POSITIVE LOGITS
    æĹłæ¯Ķ
    0.14
    iated
    0.10
    nest
    0.10
    æľīæķĪçļĦ
    0.10
     enough
    0.10
    esta
    0.10
    /power
    0.10
    ä¸įåłª
    0.09
    éļıæŶéļı
    0.09
    弩
    0.09
    Activations Density 0.022%

    No Known Activations