© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12452
    Prev
    Next
    INDEX
    Explanations

    vote, opinion, ballots

    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
    é£İéĻ©ç®¡çIJĨ
    -0.22
    terra
    -0.20
    _examples
    -0.20
    èĪĦ
    -0.19
    æĮĩæľĽ
    -0.19
    æľįåĬ¡ä¸ļ
    -0.19
    éĢĤåIJĪèĩªå·±
    -0.19
     ÑģÑĤоим
    -0.19
     займ
    -0.18
    ãĤ³ãĥŁãĥ¥
    -0.18
    POSITIVE LOGITS
     voting
    0.30
    æĬķ票
    0.30
     opinion
    0.29
    æ¯ı
    0.27
    æĦıè§ģ
    0.27
     ballots
    0.27
     vote
    0.26
     votes
    0.25
    çļĦæĦıè§ģ
    0.25
    æ¯ı人
    0.25
    Activations Density 0.039%

    No Known Activations