© 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. 22870
    Prev
    Next
    INDEX
    Explanations

    high quality

    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
    å½ĵå±Ģ
    -0.10
    ayo
    -0.09
    ÙĬات
    -0.09
    åı²ä¸ĬæľĢ
    -0.08
    éĩijçīĮ
    -0.08
    tee
    -0.08
    ÑĤол
    -0.08
    æĪIJè´¥
    -0.08
    峦
    -0.08
    æľīä¸Ģ天
    -0.08
    POSITIVE LOGITS
    ä¸Ķ
    0.12
    ä½İæĪIJæľ¬
    0.11
    /high
    0.10
    -quality
    0.10
     Maher
    0.09
    èĢĮåıĪ
    0.09
    ãģĭãģ¤
    0.09
    é«ĺåĵģè´¨
    0.09
    åľ¹
    0.09
    é«ĺè´¨éĩı
    0.09
    Activations Density 0.016%

    No Known Activations