© 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. 34493
    Prev
    Next
    INDEX
    Explanations

    ceremonies and rituals

    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
    人å±ħ
    -0.10
    åħħ
    -0.10
    è¿ŀè½½
    -0.10
    å§Ĭ妹
    -0.09
    æŀĿ
    -0.09
    èħ¾
    -0.08
    éªħ
    -0.08
    IVES
    -0.08
    ç»ıèIJ¥
    -0.08
    å§Ĭ
    -0.08
    POSITIVE LOGITS
    仪å¼ı
    0.22
    礼
    0.19
    礼仪
    0.18
    åħ¸ç¤¼
    0.17
     ceremonies
    0.15
    禮
    0.15
     ceremony
    0.14
    åĦĢ
    0.14
     rituals
    0.13
     ceremon
    0.13
    Activations Density 0.036%

    No Known Activations