© 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. 8327
    Prev
    Next
    INDEX
    Explanations

    decorative layers or finishes

    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
    yor
    -0.09
    æĬĬæı¡
    -0.09
    æ³£
    -0.09
     ÑģÑĦеÑĢе
    -0.09
    èį¯æĿIJ
    -0.09
    çĵ£
    -0.09
    aise
    -0.09
    åľ°ä¸Ĭ
    -0.08
    ä¸īå¹´
    -0.08
    ìĺ¥
    -0.08
    POSITIVE LOGITS
    åĪĩæĸŃ
    0.09
    ä¸ĭåįķ
    0.09
    èĸĦ
    0.09
    å¼Ģåħ·
    0.09
    å¼ĢäºĨ
    0.08
    å«ģ
    0.08
     Vid
    0.08
    _tolerance
    0.08
    èį¦
    0.08
    çłį
    0.08
    Activations Density 0.054%

    No Known Activations