© 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. 62100
    Prev
    Next
    INDEX
    Explanations

    lab instruction, test server, library use

    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
    åĭĴ
    -0.10
    çĶµåı°
    -0.09
    趣
    -0.09
    æŃ£æĸĩ
    -0.09
    adio
    -0.09
    æ¼ı
    -0.09
    èģĴ
    -0.08
    ãģ©ãģĵãĤį
    -0.08
    åĽ¾æĸĩ
    -0.08
    éĢļä¿Ĺ
    -0.08
    POSITIVE LOGITS
    åĢŁçĶ¨
    0.10
    èĩªä¹ł
    0.10
    åĢŁ
    0.10
    çĦ¡æĸĻ
    0.10
    åłĤ
    0.09
    ilon
    0.09
     Thesis
    0.09
    大åİħ
    0.09
    æīĵå·¥
    0.09
    å¤įåį°
    0.09
    Activations Density 0.056%

    No Known Activations