© 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. 33733
    Prev
    Next
    INDEX
    Explanations

    time units followed by time indicators

    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
    ths
    -0.10
    èī°å·¨
    -0.09
    terra
    -0.09
    æĢİä¹Īçľĭ
    -0.08
    æģ¼
    -0.08
    æł·å¼ı
    -0.08
    åĩłåı¥
    -0.08
    asio
    -0.08
    äºĽ
    -0.08
    åĩłå¼ł
    -0.08
    POSITIVE LOGITS
    è¯
    0.10
    èģĶåIJĪåĽ½
    0.10
    éªħ
    0.09
    æ³£
    0.09
    çĸļ
    0.09
    çļĦç²¾ç¥ŀ
    0.09
     freshman
    0.08
    èĥ³
    0.08
    æľįåĬ¡è´¨éĩı
    0.08
    ìĶ©
    0.08
    Activations Density 0.062%

    No Known Activations