© 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. 23080
    Prev
    Next
    INDEX
    Explanations

    save for later use

    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
    æīª
    -0.09
    çĽ¸ä¿¡å¤§å®¶
    -0.09
    讨åİĮ
    -0.09
    å¾Ĺåĩº
    -0.09
    er
    -0.09
    ÑģÑħод
    -0.09
    ç«Ļ
    -0.09
    é¼»åŃIJ
    -0.09
    oni
    -0.08
    _VM
    -0.08
    POSITIVE LOGITS
    缴åĪ°
    0.12
    à¹Ħว
    0.12
    ãģĹãģ¦ãģĬãģı
    0.10
    å¤ĩ
    0.10
    æĸ¯åŁº
    0.10
    以便
    0.10
    æľīå¾ħ
    0.09
     until
    0.09
     trữ
    0.09
    bens
    0.09
    Activations Density 0.063%

    No Known Activations