© 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. 4394
    Prev
    Next
    INDEX
    Explanations

    seek, face, with actions

    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
    æĥ³èµ·æĿ¥
    -0.10
    åIJĦä½į
    -0.09
    оÑī
    -0.09
    ties
    -0.09
    çļĦ人éĥ½
    -0.09
    大家åı¯ä»¥
    -0.09
    骤
    -0.09
    ضة
    -0.09
    åĬ¨äºº
    -0.08
    æįĨç»ij
    -0.08
    POSITIVE LOGITS
    è¿Ļ个èģĮä¸ļ
    0.14
    们
    0.12
    èģĮä¸ļéģĵå¾·
    0.11
     themselves
    0.11
     guild
    0.11
     Guild
    0.11
    èģĮä¸ļ
    0.10
    ëĭĺ
    0.10
     profession
    0.10
    åįıä¼ļ
    0.09
    Activations Density 0.389%

    No Known Activations