© 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. 4353
    Prev
    Next
    INDEX
    Explanations

    crafts and hobbies

    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
    åłĤ
    -0.09
    举
    -0.09
    ä¹İ
    -0.08
    项éĵ¾
    -0.08
    主åĬŀæĸ¹
    -0.08
    åĬ¡
    -0.08
    è·º
    -0.08
    åĮħ袱
    -0.08
    蹦
    -0.08
    èµĽ
    -0.08
    POSITIVE LOGITS
    å»ºåĽ½
    0.09
    çĶŁæ¶¯
    0.09
    ç½ij讯
    0.09
    åįıä¼ļä¼ļåijĺ
    0.09
    åĽ¤
    0.08
    èĩ³ä»Ĭ
    0.08
     вÑģÑıк
    0.08
    oola
    0.08
    å§ĭäºİ
    0.08
    åĤį
    0.08
    Activations Density 0.033%

    No Known Activations