© 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. 55851
    Prev
    Next
    INDEX
    Explanations

    that followed by a verb

    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
    ä¹Łå¥½
    -0.10
     rằng
    -0.10
    æĺ¯è°ģ
    -0.10
     Fence
    -0.09
    otta
    -0.09
    KeyType
    -0.09
    ç°ª
    -0.08
    çĸ¤
    -0.08
    并ä¸įå¤ļ
    -0.08
    ãģĦãģ¾
    -0.08
    POSITIVE LOGITS
    åħļåĴĮ
    0.09
    ÑģÑĤавка
    0.09
    волÑĮ
    0.08
    æ¸Ĭ
    0.08
    æĿ¾
    0.08
    åĴĢ
    0.08
    Provid
    0.08
    aways
    0.08
     же
    0.08
    unky
    0.08
    Activations Density 0.122%

    No Known Activations