© 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. 48532
    Prev
    Next
    INDEX
    Explanations

    proper nouns and their associations

    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
    vette
    -0.09
    æĴij
    -0.09
    éķ¿å®ī
    -0.09
    çĤķ
    -0.08
    onest
    -0.08
    ICC
    -0.08
    åĬłçĽĸ
    -0.08
    åľ¨èģĮ
    -0.08
    åij¼å£°
    -0.08
    mdb
    -0.08
    POSITIVE LOGITS
    iosa
    0.10
    ä¸Ģ个好çļĦ
    0.09
    笤
    0.09
    çľĭä¼¼
    0.08
    bubble
    0.08
     Emb
    0.08
    ãģĮãĤī
    0.08
    说å¾Ĺ
    0.08
    isi
    0.08
    ussen
    0.08
    Activations Density 0.053%

    No Known Activations