© 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. 54415
    Prev
    Next
    INDEX
    Explanations

    members, staff, guests, employees

    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¸ı
    -0.11
    ocl
    -0.10
    æĿĥå¨ģ
    -0.09
    /LICENSE
    -0.09
    æ¬Ĭ
    -0.09
    çŁ³å®¶
    -0.09
    æĪIJ为ä¸ĢåIJį
    -0.09
    ToInt
    -0.09
    女人
    -0.09
    urban
    -0.09
    POSITIVE LOGITS
    èģĮå·¥
    0.17
    åijĺå·¥
    0.15
    ä½ıæĪ·
    0.11
    åħļåijĺ
    0.11
    å¹²éĥ¨èģĮå·¥
    0.11
    å±ħæ°ij
    0.11
     staff
    0.10
     employees
    0.10
    顾客
    0.10
    åĵ¡å·¥
    0.10
    Activations Density 0.093%

    No Known Activations