© 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. 27328
    Prev
    Next
    INDEX
    Explanations

    government and administration departments

    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
    æİı
    -0.11
    çªĪ
    -0.10
    adoo
    -0.09
    å¥ł
    -0.09
    å¼Ģ工建设
    -0.08
    EntityType
    -0.08
    adesh
    -0.08
    blogs
    -0.08
    _PAIR
    -0.08
    asso
    -0.08
    POSITIVE LOGITS
    æľįåĬ¡ä¸Ńå¿ĥ
    0.14
    çŃīéĥ¨éŨ
    0.12
    管çIJĨä¸Ńå¿ĥ
    0.12
    ä¸ĵçıŃ
    0.10
    çłĶ究ä¸Ńå¿ĥ
    0.09
    åĬŀåħ¬å®¤
    0.09
     matters
    0.09
    è¾¾æłĩ
    0.09
    æĪ¡
    0.09
    çłĶ究
    0.08
    Activations Density 0.140%

    No Known Activations