© 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. 30700
    Prev
    Next
    INDEX
    Explanations

    in a sentence start

    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
    æĸ§
    -0.09
    åŀĤ
    -0.09
    åľ¨çİ°åľº
    -0.08
    DAQ
    -0.08
     Nunes
    -0.08
     vers
    -0.08
    ç°¸
    -0.08
    æĹģ
    -0.08
    uming
    -0.07
     кнопк
    -0.07
    POSITIVE LOGITS
    ç¾ģ
    0.10
    æľīä¸Ģ次
    0.09
    æĪĸèĢħ说
    0.09
    è¿Ļåı¥è¯Ŀ
    0.09
    æķħäºĭ
    0.09
    黳
    0.09
    scenario
    0.09
    第ä¸ĢæŃ¥
    0.09
    å½ĵä¹ĭ
    0.09
    çĦ¶åIJİ
    0.08
    Activations Density 0.121%

    No Known Activations