© 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. 18827
    Prev
    Next
    INDEX
    Explanations

    more or further

    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
     пÑĢид
    -0.11
    æľĢç»Ī
    -0.10
    æ¯ķç«Łæĺ¯
    -0.09
     ultimately
    -0.09
    è¿ĺä¸įå¤Ł
    -0.09
     earliest
    -0.09
    åIJİæĿ¥
    -0.08
    ForObject
    -0.08
     eventually
    -0.08
     Hann
    -0.08
    POSITIVE LOGITS
    ä¸įè¦ģåĨį
    0.12
    ä¸įä¼ļåĨį
    0.11
    åĨįä¹Ł
    0.11
     ado
    0.11
     nữa
    0.10
     anymore
    0.10
    æľīä»»ä½ķ
    0.10
     далÑĮн
    0.10
    为æŃ¢
    0.09
    ä»»ä½ķ人
    0.09
    Activations Density 0.029%

    No Known Activations