© 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. 34644
    Prev
    Next
    INDEX
    Explanations

    Albanian, Albania, Balkans

    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
    inaire
    -0.09
    æľ¬ç«Ļ
    -0.09
    çݩ游æĪı
    -0.09
    çłº
    -0.09
    åħģ
    -0.08
    loh
    -0.08
    awai
    -0.08
    æĦĨ
    -0.08
    Thai
    -0.08
    å½±åĵį
    -0.08
    POSITIVE LOGITS
     Albania
    0.12
     Alban
    0.11
    å¥ĩ
    0.11
    èĩªæ²»åĮº
    0.11
     Kosovo
    0.10
    åĮĹ约
    0.10
     Balk
    0.09
    æĤ£
    0.09
    åı£è¢ĭ
    0.09
    åİ¿å§Ķ
    0.09
    Activations Density 0.062%

    No Known Activations