© 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. 31588
    Prev
    Next
    INDEX
    Explanations

    breast milk production

    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
    çĨı
    -0.09
    åĬŁåĬĽ
    -0.09
    ç¬Ķ
    -0.09
    èĸ°
    -0.08
    ivas
    -0.08
    ä¸įèµ·
    -0.08
    åIJĬ
    -0.08
    严èĤĥ
    -0.08
    åŀĤ
    -0.08
    离
    -0.08
    POSITIVE LOGITS
    èĮħ
    0.10
    æµĵ缩
    0.09
    capt
    0.09
    太å°ij
    0.09
    çĶŁäº§ç»ıèIJ¥
    0.09
    ä¸ķ
    0.09
    STEM
    0.09
    jest
    0.09
    稳
    0.09
     citiz
    0.08
    Activations Density 0.051%

    No Known Activations