© 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. 13847
    Prev
    Next
    INDEX
    Explanations

    politics and politicians

    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
    emma
    -0.20
    è¾Ī
    -0.20
    åѦä¼ļ
    -0.20
    åĪijèѦ
    -0.19
     ÑģамоÑģÑĤоÑı
    -0.19
    æľ¬èº«å°±æĺ¯
    -0.19
    è§Ħ模æľĢ大
    -0.19
    磨
    -0.18
    æľ¬èº«å°±
    -0.18
    çĶŁçIJĨ
    -0.18
    POSITIVE LOGITS
    æĶ¿æ²»
    0.31
     political
    0.29
     politics
    0.24
    /pol
    0.24
    political
    0.24
     politician
    0.23
    (pol
    0.22
     climate
    0.22
    ista
    0.22
    é¢Ĩ导人
    0.22
    Activations Density 0.206%

    No Known Activations