© 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. 30853
    Prev
    Next
    INDEX
    Explanations

    keep _ing

    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
    ãģ¤ãģį
    -0.09
    æĦı大
    -0.09
    nga
    -0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.09
    åħ¥ãĤĬ
    -0.09
    ibu
    -0.08
    ìļ©
    -0.08
    æĶ¹åĪ¶
    -0.08
    ÑģÑĤва
    -0.08
    åĨį度
    -0.08
    POSITIVE LOGITS
    o
    0.10
    æªĢ
    0.09
    æ»Ķ
    0.09
    è¿ĽæĿ¥
    0.09
    ippy
    0.08
    请æķĻ
    0.08
    ç¬ij容
    0.08
    inement
    0.08
     positivity
    0.08
    iae
    0.08
    Activations Density 0.030%

    No Known Activations