© 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. 49885
    Prev
    Next
    INDEX
    Explanations

    place names and company suffixes

    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
    ãģ¾ãģ¾
    -0.09
    为åħ¶
    -0.09
    使åħ¶
    -0.09
     бÑĥк
    -0.08
    èĮħåı°
    -0.08
    anco
    -0.08
     prayer
    -0.08
    é²ľèĬ±
    -0.08
    keit
    -0.08
    æ´ĭèij±
    -0.08
    POSITIVE LOGITS
     Buf
    0.09
    åģļ强
    0.09
    anced
    0.09
    ä¸Ģ棵
    0.08
    æĺ¯ä¸Ģ家
    0.08
    mentioned
    0.08
     mute
    0.08
    禳
    0.08
    好çľĭ
    0.08
    ä¸Ģç«Ļ
    0.08
    Activations Density 0.002%

    No Known Activations