© 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. 26572
    Prev
    Next
    INDEX
    Explanations

    most important

    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
    åIJ¬å®Į
    -0.09
    éĢ¸
    -0.09
    éĶħ
    -0.09
    æĶ¾è¿ĩ
    -0.09
    é«ĺä½İ
    -0.09
    说å®Į
    -0.08
    ut
    -0.08
    路桥
    -0.08
    ä¸Ģå¼ł
    -0.08
    зов
    -0.08
    POSITIVE LOGITS
    thal
    0.10
    lessly
    0.09
    caler
    0.09
    æ¯Ķçİĩ
    0.09
    åľ°ä½į
    0.09
    ÃŃsimo
    0.08
    ä¾ĭå¤ĸ
    0.08
    _consts
    0.08
    eci
    0.08
    .GetAxis
    0.08
    Activations Density 0.080%

    No Known Activations