© 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. 2168
    Prev
    Next
    INDEX
    Explanations

    statin drugs

    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
    åijĺ
    -0.10
    èļķ
    -0.09
    getWindow
    -0.09
    äºĭä¸ļéĥ¨
    -0.09
    éľģ
    -0.09
    åıijå±ķçIJĨ念
    -0.08
    èĥĮåIJİ
    -0.08
    åıijå±ķæł¼å±Ģ
    -0.08
    ieee
    -0.08
    chter
    -0.08
    POSITIVE LOGITS
    æĬ¥ä¸ļ
    0.08
    å°½
    0.08
    åķĨåŁİ
    0.08
    æĬ¥ç¤¾
    0.08
    ÑıÑģÑĮ
    0.08
    飨
    0.08
    _hdl
    0.08
    .delta
    0.08
    æŀ
    0.08
    åĬ¾
    0.08
    Activations Density 0.093%

    No Known Activations