© 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. 32556
    Prev
    Next
    INDEX
    Explanations

    cup or glass of drink

    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
    åıijåĬĽ
    -0.11
    apel
    -0.10
    éĩľ
    -0.10
    æĥľ
    -0.10
    سد
    -0.09
    æĴķ
    -0.09
    èµ·ä¼ı
    -0.09
     wireType
    -0.09
    æľīæľºä¼ļ
    -0.09
    éĽ¹
    -0.09
    POSITIVE LOGITS
    ä¸ĢæĿ¯
    0.16
    æĿ¯
    0.11
    æī¶
    0.10
    æ²ı
    0.10
    çİ»çĴĥ
    0.10
    ä¸Ģç¢Ĺ
    0.10
     cup
    0.10
     glass
    0.10
     drink
    0.09
    建çŃijå·¥ç¨ĭ
    0.09
    Activations Density 0.058%

    No Known Activations