© 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. 55312
    Prev
    Next
    INDEX
    Explanations

    watching and observing events

    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
    è¯ķæİ¢
    -0.10
    身ä¸Ĭ
    -0.10
    åħ±åĴĮ
    -0.09
    æķ£åıij
    -0.09
    å§Ķå±Ī
    -0.09
    æĬĬæīĭ
    -0.09
    หล
    -0.09
    å¿Ĺ强
    -0.08
    éķ¿å¾Ĺ
    -0.08
    åijĬè¯ī大家
    -0.08
    POSITIVE LOGITS
    è§Ĥçľĭ
    0.14
    è§Ĥèµı
    0.13
    è§Ĥæij©
    0.12
    Watching
    0.11
    äº²çľ¼
    0.11
    è§ģè¯ģ
    0.11
    缮çĿ¹
    0.11
    éľĩæĴ¼
    0.11
     watching
    0.11
    åħ¨ç¨ĭ
    0.11
    Activations Density 0.083%

    No Known Activations