© 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. 20789
    Prev
    Next
    INDEX
    Explanations

    get immersed in

    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
    è¾Ĺ转
    -0.10
    æĵ¦
    -0.09
    åĪģ
    -0.09
    æİ£
    -0.09
    ç¼ĵ
    -0.09
    æĽ
    -0.08
    æĬ¬
    -0.08
    诸侯
    -0.08
    è¹Ń
    -0.08
    ÑıÑģ
    -0.08
    POSITIVE LOGITS
    æ²ī浸
    0.15
    å¿ĺ
    0.14
    æĬķåħ¥
    0.12
    æ²īæµ¸åľ¨
    0.11
    å¿ĺè®°
    0.11
     immersion
    0.10
    åħ¥å¢ĥ
    0.10
    åħ¥
    0.10
    æ·±åĪĩ
    0.10
    ãģ«åħ¥
    0.10
    Activations Density 0.057%

    No Known Activations