© 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. 51752
    Prev
    Next
    INDEX
    Explanations

    summer's arrival or end

    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
    åģļåĪ°äºĨ
    -0.10
    udo
    -0.10
    楼ä¸ĭ
    -0.10
    ÑĢак
    -0.09
    åķĥ
    -0.09
    uj
    -0.09
     ank
    -0.09
    å¿Ļ
    -0.09
    åħ³åĪĩ
    -0.09
    uela
    -0.08
    POSITIVE LOGITS
    è¾ĩ
    0.09
    vier
    0.09
    çļĦæ°Ķæģ¯
    0.09
    ãĤĴæĦŁãģĺ
    0.08
    ä¸Ģåı·
    0.08
    æ°Ķæģ¯
    0.08
    æļ¨
    0.08
     Rei
    0.08
    sav
    0.08
    åĵĪå°Ķ滨
    0.08
    Activations Density 0.046%

    No Known Activations