© 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. 11213
    Prev
    Next
    INDEX
    Explanations

    Irish language and names

    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
     Fry
    -0.09
    åijĻ
    -0.08
    ows
    -0.08
    ãĤ¾
    -0.08
    åı°ä¸Ĭ
    -0.08
    eus
    -0.08
    emann
    -0.08
    سÙĦ
    -0.08
    OND
    -0.08
     Amend
    -0.08
    POSITIVE LOGITS
    ollo
    0.10
    éĤ£ä¸ĢåĪ»
    0.09
    oris
    0.09
    WithName
    0.09
    æī¹åıijå¸Ĥåľº
    0.09
    ç¯Ŀ
    0.08
    ä¸ĢåĽ¢
    0.08
    ä¸Ģå®ļç¨ĭ度
    0.08
    ä¸Ńå°ıä¼ģä¸ļ
    0.08
    ä¹Łå°±æĺ¯è¯´
    0.08
    Activations Density 0.288%

    No Known Activations