© 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. 11294
    Prev
    Next
    INDEX
    Explanations

    ambassador or embassy

    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
    éĴ°
    -0.11
    pers
    -0.10
    åĭī
    -0.09
    allas
    -0.09
    ÑģÑı
    -0.09
    lessly
    -0.09
    ngth
    -0.09
     gou
    -0.08
    ç¼Ĩ
    -0.08
    ever
    -0.08
    POSITIVE LOGITS
    inal
    0.10
    æĪijåİ»
    0.10
    ries
    0.09
    è¡®
    0.09
    ial
    0.08
    ëĭĺ
    0.08
     Ngo
    0.08
    åĪ°ä½į
    0.08
    ย
    0.08
    atism
    0.08
    Activations Density 0.005%

    No Known Activations