© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39659
    Prev
    Next
    INDEX
    Explanations

    played by actor

    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
    é©¿ç«Ļ
    -0.09
    TAIL
    -0.09
    纾
    -0.09
    ä¸įä¸Ĭ
    -0.09
    æķ´ä¸ªäºº
    -0.08
    ãģķãģĦ
    -0.08
    åĿĩä»·
    -0.08
    ronic
    -0.08
    åħ´
    -0.08
    irie
    -0.08
    POSITIVE LOGITS
    岸
    0.11
    æ²IJ
    0.09
    å¨ģ
    0.08
    éķľå¤´
    0.08
    elden
    0.08
    åŁĭ
    0.08
    æīĭä¸ŃçļĦ
    0.08
    çĶ±
    0.07
     Dev
    0.07
    :checked
    0.07
    Activations Density 0.031%

    No Known Activations