© 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. 55944
    Prev
    Next
    INDEX
    Explanations

    Irish place names and legends

    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
    èįĴ
    -0.10
    æ²Ļæ¼ł
    -0.09
    ondon
    -0.08
    obao
    -0.08
     Paolo
    -0.08
    erek
    -0.08
    è¸ı
    -0.08
     bast
    -0.08
    ç¼Ł
    -0.08
    arkan
    -0.08
    POSITIVE LOGITS
    èµİ
    0.10
    olars
    0.10
    åħ¼
    0.10
    åĴĮå¹³
    0.09
    éĻª
    0.09
    åħ¨æĻ¯
    0.09
    enia
    0.09
    èĢ¨
    0.09
     Vikings
    0.09
    ted
    0.09
    Activations Density 0.127%

    No Known Activations