© 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. 31493
    Prev
    Next
    INDEX
    Explanations

    government officials

    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
    Restricted
    -0.10
    äºĨä¸Ģæī¹
    -0.09
    çIJĨå·¥
    -0.09
    浸
    -0.09
    å®ł
    -0.09
    ä¼´éļı
    -0.09
    çĩ¥
    -0.08
    èµĦ产éĩįç»Ħ
    -0.08
    çĶ·å£«
    -0.08
     Dawson
    -0.08
    POSITIVE LOGITS
    ä¸Ĭ级
    0.16
    åħ¨åĽ½
    0.15
    å¤ĸåľ°
    0.14
    æĢ»éĥ¨
    0.13
    大åŁİå¸Ĥ
    0.13
    åħ¨åľĭ
    0.13
    é©°æı´
    0.12
    åħ¨çľģ
    0.12
    åľ¨åħ¨åĽ½
    0.12
    å¼Ĥåľ°
    0.12
    Activations Density 0.217%

    No Known Activations