© 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. 20600
    Prev
    Next
    INDEX
    Explanations

    innovators and innovation

    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
    ncoder
    -0.09
    åĵģçīĮ形象
    -0.09
    _CHAIN
    -0.09
    reso
    -0.09
    温
    -0.09
    éŁŃ
    -0.09
    形象
    -0.08
    æ°Ĺãģ«
    -0.08
    ä»İ严治
    -0.08
    warm
    -0.08
    POSITIVE LOGITS
    åĪĽæĸ°
    0.17
     innovation
    0.17
    åĪĽæĸ°èĥ½åĬĽ
    0.16
     innovate
    0.15
     innov
    0.15
    ç§ijæĬĢåĪĽæĸ°
    0.14
    åĪĽæĸ°é©±åĬ¨
    0.13
     Innovation
    0.13
     innovations
    0.13
    åīµæĸ°
    0.13
    Activations Density 0.043%

    No Known Activations