© 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. 37454
    Prev
    Next
    INDEX
    Explanations

    can then be

    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
    åĬĽäºī
    -0.11
    iring
    -0.11
    ä¸įåºĶ该
    -0.10
    æģIJæĢķ
    -0.10
    obel
    -0.09
     дов
    -0.09
    沤
    -0.09
    è¦ģåģļ
    -0.09
    æ¯ĶåĪ©
    -0.09
    è¦ģåģļåĪ°
    -0.09
    POSITIVE LOGITS
     further
    0.14
    è¿Ľä¸ĢæŃ¥
    0.13
     далÑĮÑĪе
    0.12
     later
    0.11
    åIJİç»Ń
    0.11
    éĢ²ä¸ĢæŃ¥
    0.11
     Further
    0.10
    éļıåIJİ
    0.09
     either
    0.09
    Further
    0.09
    Activations Density 0.248%

    No Known Activations