© 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. 49928
    Prev
    Next
    INDEX
    Explanations

    programming code tokens

    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
    级以ä¸Ĭ
    -0.11
     Natalie
    -0.09
    å§Ķ
    -0.08
    âĸ¾
    -0.08
     ups
    -0.08
    å¾Īæ¸ħæ¥ļ
    -0.08
    ä¸īæľŁ
    -0.08
    ä»İäºĭ
    -0.08
    çļĦåĬĽéĩı
    -0.08
    STRU
    -0.08
    POSITIVE LOGITS
    æŶè£ħ
    0.09
    anonymous
    0.09
     Tanks
    0.09
    æīİ
    0.09
    大æĪ·
    0.09
    ÃŃn
    0.09
    æĹłæĦı
    0.09
    olu
    0.08
    uming
    0.08
    å³Ĵ
    0.08
    Activations Density 0.120%

    No Known Activations