© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8108
    Prev
    Next
    INDEX
    Explanations

    converted to other purposes or uses

    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
    Ñĩик
    -0.10
    缣
    -0.10
    æİĢ
    -0.10
    è¿Ļ座åŁİå¸Ĥ
    -0.10
    éĻ¶
    -0.10
    大è¡Ĺ
    -0.10
    äºī龸
    -0.10
    深交
    -0.10
    马路
    -0.09
    沿éĢĶ
    -0.09
    POSITIVE LOGITS
    转åĮĸ
    0.13
     conversion
    0.12
    转åĮĸ为
    0.11
    转æį¢
    0.11
    转åıĺ为
    0.11
    çĶ¨éĢĶ
    0.10
     converted
    0.10
     conversions
    0.10
     Converted
    0.10
    åı¯çĶ¨äºİ
    0.09
    Activations Density 0.253%

    No Known Activations