© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10438
    Prev
    Next
    INDEX
    Explanations

    Croatian municipalities and islands

    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
    å´ĸ
    -0.11
    orro
    -0.09
    åŃŁ
    -0.09
    å©´
    -0.09
    ARGER
    -0.09
    æĹ¥è®¯
    -0.09
    é£ŀè·ĥ
    -0.08
    çĴĭ
    -0.08
    resse
    -0.08
    åį°åº¦
    -0.08
    POSITIVE LOGITS
    Äĩ
    0.10
    æĬ¹
    0.09
    odata
    0.09
    æ²ī积
    0.09
    æ¥Ŀ
    0.08
    anja
    0.08
    iÄĩ
    0.08
    .hr
    0.08
     Balk
    0.08
     Croatian
    0.08
    Activations Density 0.258%

    No Known Activations