© 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. 56577
    Prev
    Next
    INDEX
    Explanations

    removing or removed parts

    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
    å¹½
    -0.11
    å·®è·Ŀ
    -0.10
    éļĻ
    -0.10
    åİļ度
    -0.09
    è£Ĥ
    -0.09
    峡
    -0.09
    éĻħ
    -0.09
    并ä¸į代表
    -0.09
    å¸ļ
    -0.09
     Scratch
    -0.09
    POSITIVE LOGITS
    æijĺ
    0.10
    èĦ±
    0.10
    æĬ½åĩº
    0.10
    æĬ½
    0.09
    èĦ«
    0.09
    åİ»æİī
    0.09
    Ð¡ÐŁ
    0.09
    ä¸ĭ车
    0.09
    istar
    0.09
    åıĸåĩº
    0.09
    Activations Density 0.051%

    No Known Activations