© 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. 16857
    Prev
    Next
    INDEX
    Explanations

    Democrat, Democratic, Labor Party

    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
     Quar
    -0.20
    æĬ¥çº¸
    -0.20
     discontin
    -0.20
     Buckingham
    -0.19
    ä¸įæĩĤ
    -0.19
    ç²Ĺç³Ļ
    -0.18
    å¹²çĩ¥
    -0.18
    yal
    -0.18
    ä¸į解
    -0.18
    accumulate
    -0.18
    POSITIVE LOGITS
    çī¯
    0.21
     socialist
    0.21
    æı´
    0.21
    潮湿
    0.20
     greens
    0.20
    éķı
    0.20
    moz
    0.20
    绿èī²
    0.19
     leftist
    0.19
     Greens
    0.19
    Activations Density 0.235%

    No Known Activations