© 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. 16062
    Prev
    Next
    INDEX
    Explanations

    vote or referendum

    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
    inder
    -0.20
    washer
    -0.20
    iter
    -0.19
    åīįè¾Ī
    -0.19
    æ±ŀ
    -0.18
    èĢģçīĮ
    -0.18
    domains
    -0.17
    ancel
    -0.17
    é£İåħī
    -0.17
    edu
    -0.17
    POSITIVE LOGITS
    åĨ³è®®
    0.25
    表åĨ³
    0.23
     whether
    0.23
    åĨ³èĥľ
    0.22
     turnout
    0.21
     vote
    0.21
    Whether
    0.21
     Whether
    0.20
    æĬķ票
    0.20
     decision
    0.20
    Activations Density 0.012%

    No Known Activations