© 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. 11455
    Prev
    Next
    INDEX
    Explanations

    consensus and agreement

    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
    ä¸İä¼Ĺä¸įåIJĮ
    -0.22
    (predicate
    -0.20
    Ñģи
    -0.20
    深交
    -0.20
     лиÑĩно
    -0.20
     Hague
    -0.20
     ÑĢÑıдом
    -0.19
    ç±Ģ
    -0.18
     возмож
    -0.18
    MOTE
    -0.18
    POSITIVE LOGITS
    åħ±è¯Ĩ
    0.51
     consensus
    0.43
    åħ¬è®¤
    0.35
    åħ¬è®¤çļĦ
    0.33
    ä¸Ģèĩ´
    0.31
    æĻ®éģį
    0.31
    主æµģ
    0.28
     unanim
    0.27
    大å¤ļæķ°äºº
    0.26
     unanimously
    0.25
    Activations Density 0.259%

    No Known Activations