© 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. 49058
    Prev
    Next
    INDEX
    Explanations

    Telstra, SoftBank, BellSouth, Amgen, eWEEK, Judds

    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
    oler
    -0.10
     оÑĤкÑĢÑĭва
    -0.09
    atie
    -0.09
    äºĭ项
    -0.09
    è´²
    -0.09
    æ¸Į
    -0.09
    /mit
    -0.08
    æīĺ
    -0.08
    icular
    -0.08
    æĮĩæłĩ
    -0.08
    POSITIVE LOGITS
    两æĿ¡
    0.09
    çļĦä¸ĢéĿ¢
    0.09
    é£İåIJ¹
    0.08
    æĭīä¸ģ
    0.08
    æīİ
    0.08
    æ´½
    0.08
    æĿ¡è§Ħå®ļ
    0.08
    .bam
    0.08
    èĩªçĦ¶æĺ¯
    0.08
    ä¸ĢæŃ¥
    0.08
    Activations Density 0.005%

    No Known Activations