© 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. 54950
    Prev
    Next
    INDEX
    Explanations

    cost and financial outcomes

    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
    æİī
    -0.11
     sadd
    -0.08
     benefici
    -0.08
    被人
    -0.08
    çī¹æ®ĬæĥħåĨµ
    -0.08
     Irvine
    -0.08
    å¼ĺ
    -0.08
    acre
    -0.08
    èıģ
    -0.08
     aud
    -0.08
    POSITIVE LOGITS
    室
    0.09
    zan
    0.09
    ä¸Ģ次
    0.09
    çŀĢ
    0.09
    åįĩèµ·
    0.09
     Zach
    0.09
    Gro
    0.09
    解éĩĭ
    0.08
    ä¿Ŀå®ī
    0.08
    设计çIJĨ念
    0.08
    Activations Density 0.051%

    No Known Activations