© 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. 27138
    Prev
    Next
    INDEX
    Explanations

    election winners

    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
    å¹´éĻIJ
    -0.10
    æ¿Ģ
    -0.08
    æľŁéĻIJ
    -0.08
    åĥ»
    -0.08
    anny
    -0.08
    gia
    -0.08
    æĪijçŁ¥éģĵ
    -0.08
    пÑĢод
    -0.08
    åįĩéĻį
    -0.08
    使çĶ¨å¯¿åij½
    -0.08
    POSITIVE LOGITS
    çŁ¥å·±
    0.09
    åIJĪæ³ķæĿĥçĽĬ
    0.09
    å°ıå¹ħ
    0.09
    鸳
    0.08
    loor
    0.08
    é¢ĦæĬ¥
    0.08
    ooter
    0.08
    å°¤åħ¶æĺ¯åľ¨
    0.08
    ç²īä¸Ŀ
    0.08
    丧失
    0.08
    Activations Density 0.044%

    No Known Activations