© 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. 39976
    Prev
    Next
    INDEX
    Explanations

    stages of age

    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
    æŃ¥æŃ¥
    -0.11
    妹
    -0.11
    è¶Ĭå¤ļ
    -0.10
    æĺ¯æĪijçļĦ
    -0.09
    åı©
    -0.09
    æ°¸ä¹ħ
    -0.09
    大åѦæ¯ķä¸ļ
    -0.09
    ç§įåŃIJ
    -0.09
    çIJĨä¼ļ
    -0.08
     hammer
    -0.08
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.09
     chÃŃ
    0.08
    elda
    0.08
    åıĹçIJĨ
    0.08
    uhan
    0.08
    æĿ¿æĿIJ
    0.08
    adal
    0.08
     hospitality
    0.08
    æĹ¶æľŁçļĦ
    0.08
     Lambert
    0.08
    Activations Density 0.065%

    No Known Activations