© 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. 18428
    Prev
    Next
    INDEX
    Explanations

    Kazakhstan

    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
    èµĸ
    -0.10
     sire
    -0.10
    åĥĸ
    -0.10
    çłļ
    -0.10
    æĺ¯æľī
    -0.09
    ails
    -0.09
    .rf
    -0.09
     zakÅĤad
    -0.09
    _vi
    -0.09
    ä¸Ģ声
    -0.09
    POSITIVE LOGITS
    æĸ°çĸĨ
    0.16
    ä¹Įé²ģæľ¨é½IJ
    0.13
    çĸĨ
    0.12
    è¥¿åŁŁ
    0.12
    毡
    0.11
    é¦ķ
    0.11
     Kazakhstan
    0.11
     Kaz
    0.11
    åħµåĽ¢
    0.10
    ç¾Į
    0.10
    Activations Density 0.055%

    No Known Activations