© 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. 26711
    Prev
    Next
    INDEX
    Explanations

    political offices and elections

    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
     Hyde
    -0.08
    æīĭæĮĩ
    -0.08
    Vo
    -0.08
    æħİ
    -0.08
    è´¯éĢļ
    -0.08
    容
    -0.08
    _VE
    -0.08
    éĿ¡
    -0.08
    CAF
    -0.08
     Legisl
    -0.08
    POSITIVE LOGITS
    åĢĻéĢī人
    0.11
    ç«ŀéĢī
    0.11
    ä»Ģä¹Īåij¢
    0.10
    缴åįĩ
    0.10
    çļĦéĢīæĭ©
    0.10
    åĢĻéĢī
    0.10
    人éĢī
    0.10
    çļĦç«ŀäºī
    0.09
     Barker
    0.09
    shelf
    0.09
    Activations Density 0.140%

    No Known Activations