© 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. 9087
    Prev
    Next
    INDEX
    Explanations

    UIWindow structural components

    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
    orient
    -0.09
     Orient
    -0.09
    éĨĴ缮
    -0.08
     orient
    -0.08
    æĮģä¹ħ
    -0.08
     Oriental
    -0.08
     Ñģнижен
    -0.08
    èĨĤ
    -0.08
    ä¸įåħį
    -0.08
     Dig
    -0.08
    POSITIVE LOGITS
    é£İ鼨
    0.12
    å¹ķå¢Ļ
    0.12
    ç¼ĿéļĻ
    0.10
    åĬ¨æijĩ
    0.09
    UIApplication
    0.09
    Å¡ÃŃ
    0.09
    ãģ
    0.09
    acco
    0.09
    太平æ´ĭ
    0.09
    çĻ»
    0.08
    Activations Density 0.270%

    No Known Activations