© 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. 2840
    Prev
    Next
    INDEX
    Explanations

    verbs indicating relaxation or enjoyment

    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
     _|
    -0.09
    gue
    -0.08
    鬻
    -0.08
    itet
    -0.08
    æĺ¨
    -0.08
    èį»
    -0.08
    èĢĮä¸Ķ
    -0.08
    åݻ年
    -0.08
    ç»Ļ大家
    -0.08
    éĥ¨åī¯éĥ¨éķ¿
    -0.08
    POSITIVE LOGITS
    åIJ§
    0.10
    æĦŁåıĹåĪ°
    0.09
    ç¾½
    0.09
    ç¿»å¼Ģ
    0.09
    ä¹ĭä½Ļ
    0.09
    åģļ个
    0.09
    quil
    0.09
    åıįæĺłåĩº
    0.09
    享åıĹåĪ°
    0.09
    éģĩåĪ°
    0.09
    Activations Density 0.053%

    No Known Activations