© 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. 63293
    Prev
    Next
    INDEX
    Explanations

    Swedish administrative roles

    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
    æĭĽåĭŁ
    -0.09
    andler
    -0.09
    åħ¥éŨ
    -0.09
    该éĻ¢
    -0.08
    mor
    -0.08
     Acres
    -0.08
    olest
    -0.08
    èĭĽ
    -0.08
    åħ¥æĪ·
    -0.08
    osed
    -0.08
    POSITIVE LOGITS
    æĮªå¨ģ
    0.13
    åIJīæŀĹçľģ
    0.12
    borg
    0.11
    èĬ¬åħ°
    0.11
    çijŀåħ¸
    0.11
    丹麦
    0.11
    æ²ĥå°Ķæ²ĥ
    0.10
    åIJīæŀĹ
    0.10
     Finland
    0.10
     danmark
    0.09
    Activations Density 0.406%

    No Known Activations