© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22184
    Prev
    Next
    INDEX
    Explanations

    civil war

    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
    æ´Ĵ
    -0.11
    æĸ¯åŁº
    -0.10
     pars
    -0.10
     Pars
    -0.10
     sens
    -0.09
    å®ļçĤ¹
    -0.09
    饶
    -0.09
    éIJ
    -0.08
    à¹Ģà¸Ńà¸ĩ
    -0.08
    èĤĩäºĭ
    -0.08
    POSITIVE LOGITS
    åģıåIJij
    0.10
    IRM
    0.09
     Jewel
    0.09
    佶
    0.08
    .family
    0.08
    åħŃåIJĪ
    0.08
    .updateDynamic
    0.08
     Vac
    0.08
    çĬ¹å¦Ĥ
    0.08
    åıĮåĪĽ
    0.08
    Activations Density 0.074%

    No Known Activations