© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50463
    Prev
    Next
    INDEX
    Explanations

    thoughts about

    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
    åħ·æľīä¸Ģå®ļ
    -0.10
    éªļ
    -0.10
    ä¸įåı¯
    -0.09
     somehow
    -0.09
    åģļä»Ģä¹Ī
    -0.08
    ãĤ¹ãĥĿ
    -0.08
    è§Ĵ度
    -0.08
    åħ³æ³¨åº¦
    -0.08
    ely
    -0.08
    ลำ
    -0.08
    POSITIVE LOGITS
    ç¼ĵæħ¢
    0.10
    æľīæľºä¼ļ
    0.09
    èĩ³ä»Ĭ
    0.09
    人家
    0.09
    è¿Ļ对
    0.09
    ade
    0.08
    AYER
    0.08
    åĪ°çİ°åľ¨
    0.08
    .shtml
    0.08
    éĺ¶
    0.08
    Activations Density 0.014%

    No Known Activations