© 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. 12582
    Prev
    Next
    INDEX
    Explanations

    leading, ahead, lead

    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
    urst
    -0.21
    ìŀij
    -0.20
    éģŀ
    -0.19
    èĤĩ
    -0.19
    _periods
    -0.19
    å§ĭ
    -0.19
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.19
     поÑĤом
    -0.18
    _MAXIMUM
    -0.18
    Äįe
    -0.18
    POSITIVE LOGITS
    çķ¥
    0.24
    åĬ¿å¤´
    0.22
    å¨ģèĥģ
    0.22
    迹象
    0.22
     overall
    0.21
    æ½ľåľ¨
    0.21
    æĢ»ä½ĵ
    0.21
    åŁºè°ĥ
    0.20
    åĬ¿
    0.20
    iscal
    0.20
    Activations Density 0.019%

    No Known Activations