© 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. 48134
    Prev
    Next
    INDEX
    Explanations

    Greens, green, fairways

    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
    èĻ½çĦ¶æĺ¯
    -0.10
    Slim
    -0.10
     tiết
    -0.09
    ëij¥
    -0.09
    亲
    -0.09
    æµĶ
    -0.09
    åĩºçĶŁ
    -0.09
     Quit
    -0.09
    çĺ¦
    -0.09
    ãĥĺãĥ«
    -0.09
    POSITIVE LOGITS
    åĿª
    0.09
    åı¯è§Ĩ
    0.08
    ald
    0.08
    acy
    0.08
    çıī
    0.08
    ook
    0.08
     dansk
    0.08
    主任
    0.08
    èĥ¥
    0.08
    åĪĹ
    0.07
    Activations Density 0.003%

    No Known Activations