© 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. 2720
    Prev
    Next
    INDEX
    Explanations

    capital cities

    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
    å¼ºåĽ½
    -0.10
    ç¾İ人
    -0.09
    itarian
    -0.09
    Trap
    -0.09
    åľ¨æľªæĿ¥
    -0.08
    åİ¿å§Ķ书记
    -0.08
    ãĤ·ãĤ¢
    -0.08
    溷
    -0.08
    æĢ§å¼º
    -0.08
    欸
    -0.08
    POSITIVE LOGITS
    åŃľ
    0.09
    çķĻç»Ļ
    0.09
    _ASS
    0.08
    æ·±å¤Ħ
    0.08
     Bender
    0.08
    åIJĿ
    0.08
     trous
    0.08
    æĽ´å¥½åľ°
    0.08
     Ap
    0.08
    éĩĮçļĦ
    0.08
    Activations Density 0.014%

    No Known Activations