© 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. 17116
    Prev
    Next
    INDEX
    Explanations

    water damage and rescue

    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
    ç»Ń
    -0.10
    æĺ¥ç§ĭ
    -0.10
    .getAttribute
    -0.09
    aille
    -0.09
    getAttribute
    -0.09
    æĸ©
    -0.09
    uries
    -0.08
     blas
    -0.08
    çĹī
    -0.08
    饿
    -0.08
    POSITIVE LOGITS
    å¿ĥçĸ¼
    0.10
    æĮİ
    0.10
    ä¸ĢéĶ®
    0.09
    æ¸į
    0.09
    æįŁå®³
    0.09
    ä¸ĢæĿ¡é¾Ļ
    0.09
    æĹĭ
    0.09
    .rf
    0.09
    æ»Ķ
    0.09
    metis
    0.09
    Activations Density 0.086%

    No Known Activations