© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6695
    Prev
    Next
    INDEX
    Explanations

    weekend getaway

    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
    ä¸įç»ı
    -0.09
    礼è²Į
    -0.09
    ipy
    -0.09
    ä»°
    -0.09
    æĪ¿è´·
    -0.09
    å¾Ĵ
    -0.08
    atorium
    -0.08
    æİĮ声
    -0.08
    俯
    -0.08
    åİħ
    -0.07
    POSITIVE LOGITS
    ç¥ŀåĻ¨
    0.09
    .returnValue
    0.09
    éķ¿å®ī
    0.09
    inth
    0.09
    ivr
    0.09
    èݳ
    0.08
     nid
    0.08
    asl
    0.08
    çĻ½é©¬
    0.08
     tá»ĵ
    0.08
    Activations Density 0.035%

    No Known Activations