© 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. 29850
    Prev
    Next
    INDEX
    Explanations

    detention and detainment

    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
    -0.12
    oft
    -0.10
    大楼
    -0.09
    ÑģÑĤÑĢой
    -0.09
    æĬľ
    -0.09
    ness
    -0.08
    å¢ĥçķĮ
    -0.08
    ophone
    -0.08
    åĪĩåħ¥
    -0.08
    ãģ¨ãģĦãģ£ãģ¦
    -0.08
    POSITIVE LOGITS
    ä½ıäºĨ
    0.14
    ä¸įä½ı
    0.14
    ä½ı
    0.10
    å·²ä¹ħçļĦ
    0.10
    erval
    0.09
    éĻIJãĤĬ
    0.09
    opus
    0.09
    å¾Ĺä½ı
    0.08
    縻
    0.08
    ł
    0.08
    Activations Density 0.011%

    No Known Activations