© 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. 9904
    Prev
    Next
    INDEX
    Explanations

    reflection

    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
    èĪĴ
    -0.10
    ç¿ģ
    -0.10
    Thin
    -0.09
    èĬĻèĵī
    -0.09
    åĭŁ
    -0.09
    anter
    -0.09
    诸
    -0.09
    ç»Ĩç»Ĩ
    -0.09
     coll
    -0.09
    諸
    -0.08
    POSITIVE LOGITS
     bounce
    0.10
    被åĬ¨
    0.10
    åī¥
    0.10
     Minerals
    0.09
    åıįå°Ħ
    0.09
    ä¸ĢæĬ¹
    0.09
    伺æľį
    0.09
    漫
    0.09
    åŁĻ
    0.09
     bouncing
    0.09
    Activations Density 0.074%

    No Known Activations