© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36956
    Prev
    Next
    INDEX
    Explanations

    external elements or locations

    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
    åĨħåľ¨
    -0.10
    åľ¨éĩĮéĿ¢
    -0.09
    ç§ijåĪĽæĿ¿
    -0.09
    å½ĵä¹ĭ
    -0.09
    åĨħåľ°
    -0.09
     Seymour
    -0.09
    ä¸Ńæŀ¢
    -0.08
    åĨħéĥ¨
    -0.08
     central
    -0.08
    rais
    -0.08
    POSITIVE LOGITS
    å¤ĸéĥ¨
    0.23
    åľ¨å¤ĸéĿ¢
    0.22
    å¤ĸéĿ¢
    0.21
    æł¡å¤ĸ
    0.20
    outside
    0.20
     Outside
    0.20
     outside
    0.20
     внеÑĪ
    0.20
     external
    0.20
    Outside
    0.19
    Activations Density 0.279%

    No Known Activations