© 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. 53841
    Prev
    Next
    INDEX
    Explanations

    Ireland and related countries

    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
    个åĪ«
    -0.10
    æķĪ
    -0.09
    éĥĵ
    -0.09
     ÐŁÐ°
    -0.09
    ä¸įå¾Ĺ转载
    -0.09
    صب
    -0.09
    æľ¬ç«Ļ
    -0.09
    ittest
    -0.09
     Barth
    -0.09
    ç¾½
    -0.09
    POSITIVE LOGITS
    è¦Ĩ
    0.10
    çĶĺ
    0.10
    ç¾ĬèĤī
    0.10
     Locker
    0.08
     canada
    0.08
     Spo
    0.08
    æ¸ħè¿ľ
    0.08
    çĸĨ
    0.08
    æ°ijæĹıæĸĩåĮĸ
    0.08
     Submitted
    0.08
    Activations Density 0.178%

    No Known Activations