© 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. 5453
    Prev
    Next
    INDEX
    Explanations

    rides and slides

    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
    éĩĬ
    -0.10
    ä¹ĭéģĵ
    -0.09
    giene
    -0.09
    iset
    -0.09
    èµĥ
    -0.09
    客æĪ·éľĢæ±Ĥ
    -0.09
    éĩĭ
    -0.08
    ç¬Ļ
    -0.08
    igure
    -0.08
    aset
    -0.08
    POSITIVE LOGITS
    åħĪæĬĬ
    0.08
    ack
    0.08
    京津
    0.08
    彩èĻ¹
    0.08
     ëĶ°
    0.08
    ÙĪÙĦا
    0.07
    ä¸įåıĬ
    0.07
    æ°ijèIJ¥ç»ıæµİ
    0.07
    æĿ¯
    0.07
     updatedAt
    0.07
    Activations Density 0.012%

    No Known Activations