© 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. 2899
    Prev
    Next
    INDEX
    Explanations

    try demos and tests

    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
    ç¼ĿéļĻ
    -0.08
     constitutional
    -0.08
    é¢Ŀ
    -0.08
    éĢŁåº¦å¿«
    -0.08
    ä¹ĺ
    -0.07
    æŃ¥
    -0.07
    ÖĦ
    -0.07
    乡
    -0.07
    عاÙĨ
    -0.07
     Moder
    -0.07
    POSITIVE LOGITS
    æł·
    0.13
    çļĦå®ŀéĻħ
    0.12
    è¯ķ
    0.12
    è¯ķè¯ķ
    0.11
    æł·åĵģ
    0.11
    è¯ķçĤ¹
    0.11
    Before
    0.10
    å°Ŀ
    0.10
    樣
    0.10
     trial
    0.10
    Activations Density 0.107%

    No Known Activations