© 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. 21574
    Prev
    Next
    INDEX
    Explanations

    game final moments

    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
    åľ¨äº¬
    -0.10
    æī«ä¸Ģæī«
    -0.10
    æ´»åĬ¨ä¸Ń
    -0.09
     Att
    -0.09
    æĹ©å°±
    -0.09
    att
    -0.08
    leased
    -0.08
    ä¾®
    -0.08
    俯
    -0.08
     cle
    -0.08
    POSITIVE LOGITS
    æľĢåIJİä¸Ģ
    0.15
    åĨ³èĥľ
    0.11
    æľĢåIJİ
    0.11
     final
    0.11
    åħ³éĶ®æŶåĪ»
    0.10
     ÑĢеÑĪа
    0.10
     Final
    0.10
     FINAL
    0.10
    /moment
    0.09
    åĬŁ
    0.09
    Activations Density 0.044%

    No Known Activations