© 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. 53638
    Prev
    Next
    INDEX
    Explanations

    lack of merit or substance

    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
    çĸ¾
    -0.09
    ients
    -0.09
    åħ¨ç¤¾ä¼ļ
    -0.08
    èĺ¼
    -0.08
    åħ¬è®¤çļĦ
    -0.08
    åİĨç¨ĭ
    -0.08
    æķ£æĸĩ
    -0.08
    ä¸įä¿¡
    -0.08
    åĩłçĤ¹
    -0.08
    neo
    -0.08
    POSITIVE LOGITS
    åĢ¼å¾Ĺä¸Ģ
    0.11
    å°±è¿Ļæł·
    0.11
    çIJĨ
    0.10
    ä¾Ŀæĵļ
    0.10
    ä¾Ŀæį®
    0.10
    ä¹Ŀ大
    0.09
    ä¸ľäº¬
    0.09
    .sound
    0.09
    æįı
    0.09
    ä¸Ģçľĭ
    0.09
    Activations Density 0.173%

    No Known Activations