© 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. 3442
    Prev
    Next
    INDEX
    Explanations

    Swedish places 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
    产åѦçłĶ
    -0.10
    è¡Ķ
    -0.10
    庾
    -0.10
     Buchanan
    -0.09
    åĪ°åºķ
    -0.09
    urch
    -0.09
    俯
    -0.08
    ä¿İ
    -0.08
    å³Ĵ
    -0.08
    æľ¬äºº
    -0.08
    POSITIVE LOGITS
    çijŀåħ¸
    0.24
    æĮªå¨ģ
    0.18
    丹麦
    0.17
     Swedish
    0.17
    åIJīæŀĹçľģ
    0.17
     Sweden
    0.16
     Stockholm
    0.15
    èĬ¬åħ°
    0.14
     Lund
    0.14
    Sweden
    0.14
    Activations Density 0.401%

    No Known Activations