© 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. 5726
    Prev
    Next
    INDEX
    Explanations

    is/was/has followed by 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
    é¹Ń
    -0.11
    èĢĮåİ»
    -0.10
    æľīæľŁ
    -0.10
    åı¯æĥ³èĢĮçŁ¥
    -0.10
    ĮĢ
    -0.09
    为åħ¶
    -0.09
    apl
    -0.09
    é¦
    -0.09
    æ·ŀ
    -0.09
    æİ¥è¿ij
    -0.09
    POSITIVE LOGITS
    æıIJé«ĺ
    0.09
    .orig
    0.09
    ä»Ĭ
    0.09
    æĥħ人
    0.08
    æĺİ天
    0.08
     dick
    0.08
    å±ķå¼Ģ
    0.08
    ãģªãģĭ
    0.08
    êm
    0.07
    æĸŁ
    0.07
    Activations Density 0.213%

    No Known Activations