© 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. 12246
    Prev
    Next
    INDEX
    Explanations

    elected for council seats

    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
    ĥģ
    -0.19
    allax
    -0.19
    å¥ı
    -0.18
    éĢĨ转
    -0.18
    æ¯ģçģŃ
    -0.18
     marital
    -0.18
    -shift
    -0.17
    ä¸ĢéĹª
    -0.17
    Processed
    -0.17
    å«Ĥ
    -0.17
    POSITIVE LOGITS
    éĢī举
    0.32
    éĢīåĩº
    0.29
    ä¸Ĭå²Ĺ
    0.27
    å½ĵéĢī
    0.27
     elected
    0.26
     elections
    0.25
     election
    0.24
    election
    0.24
    disk
    0.24
    ä»»æľŁ
    0.23
    Activations Density 0.109%

    No Known Activations