© 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. 33171
    Prev
    Next
    INDEX
    Explanations

    weight loss

    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
    ness
    -0.11
    ä¸įæ¸ħ
    -0.10
    丰å¯Įå¤ļ彩
    -0.10
    ssc
    -0.10
    USTER
    -0.09
    ä¸Ģ大åłĨ
    -0.09
    ä¸ĭ车
    -0.09
    ity
    -0.09
    éĴī
    -0.09
    erness
    -0.09
    POSITIVE LOGITS
    æŶ任
    0.11
    вед
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    å¹ħ度
    0.08
    orde
    0.08
    åIJİåĨį
    0.08
     بت
    0.08
    åĨ³å¿ĥ
    0.08
    æĪIJ为ä¸Ģ个
    0.08
    isy
    0.08
    Activations Density 0.014%

    No Known Activations