© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16599
    Prev
    Next
    INDEX
    Explanations

    republicans or repuglicans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    enticator
    -0.19
    -Pacific
    -0.18
    erot
    -0.17
    thon
    -0.17
    eron
    -0.17
    melon
    -0.16
    baugh
    -0.16
    ered
    -0.16
    phans
    -0.16
    èĢģ人
    -0.15
    POSITIVE LOGITS
     Ñģобой
    0.20
    nik
    0.20
    itory
    0.17
    лÑİ
    0.17
    ëĭĪëĭ¤
    0.17
    ertoire
    0.17
    ucc
    0.16
    缯
    0.16
    们
    0.16
    oxid
    0.16
    Activations Density 0.017%

    No Known Activations