© 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. 20422
    Prev
    Next
    INDEX
    Explanations

    gold, silver, bronze medals

    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
    éŁ³
    -0.09
     Neo
    -0.09
    æĹħ
    -0.09
    olon
    -0.09
     ÐľÐ¾Ñģ
    -0.09
    OLON
    -0.08
    æį½
    -0.08
    ç¥ŀå·ŀ
    -0.08
    dsl
    -0.08
     ÑĤеÑĢÑĢиÑĤоÑĢ
    -0.08
    POSITIVE LOGITS
    çĻ½éĵ¶
    0.10
    mine
    0.10
    ä¿Ĺè¯Ŀ说
    0.10
     mine
    0.10
    åĽ½éĻħåľ¨çº¿
    0.09
     silver
    0.09
    etta
    0.09
    zier
    0.09
    çŁ¿ä¸ļ
    0.09
    ilver
    0.09
    Activations Density 0.064%

    No Known Activations